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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and statistical values

    oai_token-act-pair · gpt-3.5-turbo

    statistical terms and values related to experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.69
    inventoryQuantity
    -0.64
    anza
    -0.61
     packages
    -0.60
     Codex
    -0.56
     offerings
    -0.56
     hostage
    -0.55
     lett
    -0.55
    elist
    -0.55
    kas
    -0.54
    POSITIVE LOGITS
    003
    0.91
    002
    0.90
    0001
    0.84
    005
    0.84
    007
    0.82
    009
    0.81
    heter
    0.81
    017
    0.80
    006
    0.80
    004
    0.79
    Act Density 0.039%

    No Known Activations