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

    Neuronpedia

    INDEX
    Explanations

    words that express uncertainty or moderation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.19
    еÑī
    -0.17
    sport
    -0.16
    sing
    -0.15
    fty
    -0.14
    axter
    -0.14
    Ïĥμ
    -0.14
    isable
    -0.14
    izational
    -0.14
    odb
    -0.13
    POSITIVE LOGITS
    ewhat
    0.14
    ebb
    0.14
    uario
    0.13
    StandardItem
    0.13
    CJK
    0.13
    Ĥ¨
    0.13
    /stdc
    0.13
    onth
    0.12
    º«
    0.12
    rag
    0.12
    Act Density 0.012%

    No Known Activations