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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or strong expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erb
    -0.16
    istrovstvÃŃ
    -0.16
    ulace
    -0.15
    ahoma
    -0.15
    ursal
    -0.14
    allas
    -0.14
    ảo
    -0.14
    aised
    -0.14
    'Neill
    -0.14
    GenerationStrategy
    -0.14
    POSITIVE LOGITS
     Dunn
    0.18
    dal
    0.17
     dispens
    0.16
     Orth
    0.15
    arya
    0.14
     Rex
    0.14
     ray
    0.14
    İ·
    0.14
     dict
    0.14
    UTTON
    0.14
    Act Density 0.052%

    No Known Activations