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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by a hyphen and a word or phrase

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Wem
    -1.01
    ILLE
    -0.94
     Bulg
    -0.94
    assetsadobe
    -0.93
     Pry
    -0.88
     BMC
    -0.86
    Pg
    -0.85
    BIL
    -0.84
     roadside
    -0.83
     welf
    -0.81
    POSITIVE LOGITS
    verting
    1.55
    structed
    1.54
    naissance
    1.52
    verted
    1.50
    vert
    1.45
    currency
    1.43
    cerned
    1.42
    joined
    1.39
    secut
    1.36
    vention
    1.35
    Act Density 0.370%

    No Known Activations