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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anonymous sources or conditions of anonymity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predetermined terms or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umerable
    -0.73
    aces
    -0.70
    thal
    -0.69
    arij
    -0.69
    encer
    -0.68
    riks
    -0.67
    clipse
    -0.65
     Highlander
    -0.64
    gall
    -0.63
    umbn
    -0.62
    POSITIVE LOGITS
     confir
    0.81
     caveat
    0.79
     indemn
    0.75
     anonymity
    0.72
     preserving
    0.71
     unspecified
    0.68
    idential
    0.67
     elabor
    0.66
     agreeing
    0.66
     guarant
    0.65
    Act Density 0.025%

    No Known Activations