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

    Neuronpedia

    INDEX
    Explanations

    political rhetoric and statements related to various policies and conflicts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rients
    -0.69
    cot
    -0.63
    rient
    -0.62
    essa
    -0.61
    ESCO
    -0.56
    opia
    -0.56
     Skydragon
    -0.55
    TAIN
    -0.54
    itial
    -0.54
     Restaur
    -0.53
    POSITIVE LOGITS
    mith
    0.81
     uttered
    0.72
     spoken
    0.70
    anguage
    0.67
    storms
    0.64
     eloqu
    0.62
     surrounding
    0.62
     guiActiveUn
    0.62
    mouth
    0.62
     emanating
    0.61
    Act Density 12.534%

    No Known Activations