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

    Neuronpedia

    INDEX
    Explanations

    adverbs that modify adjectives or verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IID
    -0.15
    porn
    -0.15
    ave
    -0.15
    icos
    -0.14
    rawer
    -0.14
    販
    -0.14
    licht
    -0.14
     Woodward
    -0.13
    imei
    -0.13
    /classes
    -0.13
    POSITIVE LOGITS
    uang
    0.15
    lık
    0.15
    .generated
    0.14
    ÑĦоÑĢ
    0.14
    ,},↵
    0.14
     fore
    0.14
     finite
    0.14
    ptrdiff
    0.13
    escort
    0.13
    -begin
    0.13
    Act Density 0.050%

    No Known Activations