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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fill" and its variations, indicating contexts related to filling spaces or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eph
    -0.16
    /from
    -0.16
    ishi
    -0.16
    ely
    -0.16
    annis
    -0.15
    dg
    -0.14
    _FIFO
    -0.14
    esis
    -0.14
     Shaw
    -0.14
    ed
    -0.13
    POSITIVE LOGITS
    åIJįçĦ¡ãģĹãģķãĤĵ
    0.16
    .Bind
    0.15
    fill
    0.14
    iterals
    0.14
    Argb
    0.14
    -up
    0.14
    brook
    0.14
    mates
    0.14
    filled
    0.14
    retch
    0.14
    Act Density 0.042%

    No Known Activations