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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions using variables and operators

    oai_token-act-pair · gpt-3.5-turbo

    mathematical or programming expressions related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indust
    -0.85
     Flavoring
    -0.72
     USPS
    -0.65
     invitations
    -0.65
    naissance
    -0.65
    assets
    -0.64
    international
    -0.63
    accompan
    -0.62
    Organ
    -0.62
    å§
    -0.61
    POSITIVE LOGITS
     =>
    0.77
     ->
    0.74
    uments
    0.72
     <=
    0.72
    seq
    0.71
     =
    0.70
    ^{
    0.69
     theorem
    0.69
    args
    0.68
     ,
    0.68
    Act Density 0.098%

    No Known Activations