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

    Neuronpedia

    INDEX
    Explanations

    locations or places mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cknow
    -0.99
    cknowled
    -0.97
    chieve
    -0.90
    amily
    -0.89
     Flavoring
    -0.83
     Extras
    -0.80
    reditary
    -0.80
    tiny
    -0.79
    vec
    -0.78
     LIST
    -0.78
    POSITIVE LOGITS
     than
    0.96
    rant
    0.94
    sex
    0.90
    Root
    0.88
     principals
    0.87
    azaki
    0.86
     imaginable
    0.86
    ulative
    0.84
     applies
    0.83
    ãĤ¹ãĥĪ
    0.82
    Act Density 1.431%

    No Known Activations