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

    Neuronpedia

    INDEX
    Explanations

    evidence of the word "so" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    craft
    -0.18
    .habbo
    -0.15
    umm
    -0.15
    Ñĩ
    -0.15
    kr
    -0.14
    cko
    -0.14
    enal
    -0.13
    ë¦ī
    -0.13
    aval
    -0.13
    kaar
    -0.13
    POSITIVE LOGITS
    -called
    0.24
    ìį¨
    0.16
    ester
    0.16
     tam
    0.15
     far
    0.15
    fern
    0.15
    yer
    0.14
    onest
    0.14
    thew
    0.14
    <img
    0.14
    Act Density 0.075%

    No Known Activations