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

    Neuronpedia

    INDEX
    Explanations

    parts of language that suggest complex constructs and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iel
    -0.16
    _SYNC
    -0.15
    ازÙħ
    -0.14
     envelop
    -0.14
    åĩº
    -0.14
    upt
    -0.14
    anic
    -0.14
    лиз
    -0.14
    iyat
    -0.13
    çŁ¥
    -0.13
    POSITIVE LOGITS
    ings
    0.19
    ungen
    0.17
    osing
    0.17
    ingen
    0.16
    ingham
    0.16
    ensburg
    0.16
    edes
    0.15
    endment
    0.15
    enment
    0.15
    ingly
    0.15
    Act Density 0.052%

    No Known Activations