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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptive phrases related to items and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.80
     myſelf
    -0.70
     فريبيس
    -0.69
    ſelf
    -0.69
     juſ
    -0.68
     themſelves
    -0.67
     purpoſe
    -0.67
     houſe
    -0.66
     Majefty
    -0.65
    脚注の使い方
    -0.65
    POSITIVE LOGITS
     small
    0.75
     large
    0.63
     tiny
    0.63
     little
    0.58
     occasional
    0.58
     неболь
    0.57
    hasMoreElements
    0.57
     mini
    0.56
     a
    0.55
    him
    0.54
    Act Density 0.317%

    No Known Activations