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

    Neuronpedia

    INDEX
    Explanations

    mentions of Charles Darwin and evolutionary concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    entials
    -0.58
    atile
    -0.58
    incerity
    -0.52
    uds
    -0.51
    MENTS
    -0.50
    itcher
    -0.50
     captcha
    -0.49
    onder
    -0.49
    spring
    -0.48
    eah
    -0.47
    POSITIVE LOGITS
    sey
    0.64
     Darwin
    0.56
    aminer
    0.55
    istic
    0.55
     Chronicle
    0.53
    ism
    0.52
    iously
    0.52
    arium
    0.52
    nect
    0.51
    Ĥİ
    0.51
    Act Density 8.157%

    No Known Activations