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

    Neuronpedia

    INDEX
    Explanations

    terms indicating uniqueness or significant characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.57
     againſt
    -0.53
    ajemy
    -0.51
     invloed
    -0.49
     partiellement
    -0.49
     ſeveral
    -0.48
    ğimiz
    -0.48
    Wall
    -0.47
    Useful
    -0.47
    Seine
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.77
    styleable
    0.68
    fillType
    0.61
    aarrggbb
    0.59
    rungsseite
    0.58
     unknownFields
    0.58
     disambiguazione
    0.55
    permum
    0.55
    Beschreibung
    0.55
    rrggbb
    0.54
    Act Density 0.501%

    No Known Activations