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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     corners
    -0.82
     commissions
    -0.81
     "$:/
    -0.77
    hin
    -0.77
     highways
    -0.74
     territ
    -0.72
    yg
    -0.72
     tumble
    -0.71
     bridges
    -0.70
    orah
    -0.69
    POSITIVE LOGITS
    URA
    0.79
    Transfer
    0.79
    RF
    0.79
    hematically
    0.73
     VO
    0.72
    VALUE
    0.69
    usage
    0.68
    BIL
    0.68
    Enh
    0.68
    abil
    0.68
    Act Density 19.526%

    No Known Activations