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

    Neuronpedia

    INDEX
    Explanations

    mentions of percentages and their implications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    談社
    -0.95
     roulant
    -0.88
     uſe
    -0.87
     himſelf
    -0.86
     raiſ
    -0.85
     pleaſure
    -0.85
     Efq
    -0.83
     uſed
    -0.81
     cauſe
    -0.80
     caufe
    -0.76
    POSITIVE LOGITS
    mybatisplus
    0.88
    hdashline
    0.77
    bigoplus
    0.73
    ment
    0.72
    ią
    0.71
    en
    0.69
     Prozent
    0.69
     trent
    0.69
    '));
    0.68
     Chaudh
    0.67
    Act Density 0.011%

    No Known Activations