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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or states involving significant occurrences or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppins
    -0.16
    verity
    -0.15
     indeb
    -0.15
    ritt
    -0.14
    aping
    -0.14
    uguay
    -0.14
    SetTitle
    -0.14
    ongyang
    -0.14
    olon
    -0.14
    rts
    -0.14
    POSITIVE LOGITS
    _OBJECT
    0.14
     demand
    0.14
    ultz
    0.14
    zens
    0.13
    demand
    0.13
     Object
    0.13
    able
    0.13
    леÑĩ
    0.13
     Chest
    0.13
    infeld
    0.13
    Act Density 0.008%

    No Known Activations