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

    Neuronpedia

    INDEX
    Explanations

    intensifiers followed by adjectives or adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lip
    -0.15
    sten
    -0.15
    ustr
    -0.15
    UBY
    -0.14
    lot
    -0.14
    lix
    -0.14
    too
    -0.14
    изнеÑģ
    -0.14
    plit
    -0.14
    ZY
    -0.14
    POSITIVE LOGITS
    Ïĩε
    0.15
    Ñĩи
    0.15
     -*-č↵
    0.14
    ething
    0.14
    ythe
    0.14
    untu
    0.13
    .documentation
    0.13
    alara
    0.13
    lingen
    0.13
     much
    0.13
    Act Density 0.018%

    No Known Activations