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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions and legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ycz
    -0.18
    indow
    -0.16
     اÙĦÙħÙĤ
    -0.16
    ully
    -0.15
     ür
    -0.15
    RATION
    -0.15
    _CHANGED
    -0.14
    Plane
    -0.14
    arel
    -0.14
    ÑĢÑıд
    -0.14
    POSITIVE LOGITS
    ayar
    0.17
     bar
    0.17
     Corporate
    0.17
     Bans
    0.16
     Bl
    0.16
    xAD
    0.16
     corporate
    0.15
    ktor
    0.15
     bl
    0.15
     Win
    0.14
    Act Density 0.022%

    No Known Activations