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

    Neuronpedia

    INDEX
    Explanations

    emotive language and expressions related to vulnerability and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     GenerationType
    -0.63
     ویکی‌پدیا
    -0.62
     surla
    -0.56
    lizard
    -0.55
    chuhe
    -0.53
    onda
    -0.52
     contigo
    -0.52
     vere
    -0.52
    unjang
    -0.52
    POSITIVE LOGITS
     impressive
    0.80
    tably
    0.71
     glorious
    0.70
     delightful
    0.70
    ciless
    0.69
    rited
    0.68
    ly
    0.68
    spirited
    0.68
    delicious
    0.67
     oprot
    0.67
    Act Density 0.427%

    No Known Activations