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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically those related to historical figures and locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    skirts
    -0.66
    âĶģ
    -0.60
    åŃ
    -0.58
    DIV
    -0.56
    icable
    -0.55
    ODUCT
    -0.53
    é¾įå¥ij士
    -0.52
     Forbidden
    -0.52
     Concern
    -0.51
    earance
    -0.50
    POSITIVE LOGITS
    hart
    0.86
    ardo
    0.82
     Trotsky
    0.79
    hardt
    0.78
    idas
    0.76
    ette
    0.72
    hard
    0.71
    orian
    0.69
    utenant
    0.69
    idates
    0.69
    Act Density 6.304%

    No Known Activations