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

    Neuronpedia

    INDEX
    Explanations

    negative statements or rejections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.63
    ViewFeatures
    -0.58
    cinoma
    -0.56
    ♂
    -0.56
     незавершена
    -0.56
    expandindo
    -0.56
    ftagPool
    -0.56
     quæ
    -0.56
    PARATUS
    -0.55
    ANY
    -0.55
    POSITIVE LOGITS
     longer
    0.81
     doubt
    0.61
    tica
    0.58
     different
    0.53
     lon
    0.53
    bodies
    0.53
    isome
    0.53
    isier
    0.52
     beda
    0.50
     exception
    0.50
    Act Density 0.118%

    No Known Activations