Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific experiments or studies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to experimental processes or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veland
    -0.84
    andra
    -0.78
    utra
    -0.75
    ithing
    -0.73
    HCR
    -0.71
    atra
    -0.71
    olulu
    -0.71
    bery
    -0.70
    words
    -0.70
    criptions
    -0.69
    POSITIVE LOGITS
    imental
    0.94
     Prototype
    0.74
     Experimental
    0.73
    ists
    0.73
     experimental
    0.72
     laboratory
    0.72
     findings
    0.70
     licence
    0.69
     psychologists
    0.69
     manip
    0.69
    Act Density 0.015%

    No Known Activations