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

    Neuronpedia

    INDEX
    Explanations

    proper nouns ending in 'ker' with varying degrees of specificity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ker" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cind
    -0.75
    UME
    -0.73
    erest
    -0.71
    eree
    -0.64
     haste
    -0.64
    ancies
    -0.61
    IRD
    -0.60
    UE
    -0.59
    ental
    -0.59
    ERROR
    -0.59
    POSITIVE LOGITS
    chief
    1.07
    ker
    1.02
    lund
    0.93
    lar
    0.87
    lein
    0.86
    icker
    0.84
    geon
    0.82
    pedia
    0.82
    rigan
    0.81
    king
    0.80
    Act Density 0.015%

    No Known Activations