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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on" and phrases related to ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quan
    -0.15
    й
    -0.15
    (disposing
    -0.14
    les
    -0.14
    ãģıãģł
    -0.13
    edic
    -0.13
    sse
    -0.13
    лек
    -0.13
    chet
    -0.13
    leck
    -0.13
    POSITIVE LOGITS
     behalf
    0.18
    .datas
    0.15
    otta
    0.15
     Butt
    0.15
    ãĥ¢ãĥ³
    0.14
     Dough
    0.14
    ĥn
    0.14
    ried
    0.14
     dil
    0.13
    ynchronously
    0.13
    Act Density 0.041%

    No Known Activations