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

    Neuronpedia

    INDEX
    Explanations

    personal stories or anecdotes shared anonymously

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.73
    AddWithValue
    -0.72
    Subjects
    -0.68
    Во
    -0.67
    import
    -0.67
    Wy
    -0.64
    WriteLiteral
    -0.64
    port
    -0.63
    break
    -0.63
    term
    -0.63
    POSITIVE LOGITS
     maneu
    1.66
     indestru
    1.46
     lamborghini
    1.44
     mondeo
    1.43
     reluct
    1.43
     scrat
    1.41
     fortn
    1.41
     shenan
    1.39
     squa
    1.38
     emphat
    1.37
    Act Density 0.194%

    No Known Activations