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

    Neuronpedia

    INDEX
    Explanations

    comparative terms indicating differences in measurement or performance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Theſe
    -0.88
     myſelf
    -0.87
     ſeveral
    -0.86
     Monfieur
    -0.82
    ituary
    -0.81
     NSCoder
    -0.80
    ArrowToggle
    -0.79
     itſelf
    -0.75
     iſt
    -0.73
     faſt
    -0.73
    POSITIVE LOGITS
     typelib
    0.52
    httphttps
    0.51
    (&:
    0.50
    <?
    0.50
     חיצוניים
    0.46
     T
    0.46
    Tē
    0.45
    __.__
    0.45
    chapper
    0.44
    最快更新
    0.44
    Act Density 0.057%

    No Known Activations