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

    Neuronpedia

    INDEX
    Explanations

    references to academic or scholarly publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulents
    -0.60
     replacement
    -0.56
    npmjs
    -0.54
     replacements
    -0.54
    endency
    -0.53
    uttosto
    -0.53
    ntö
    -0.53
    LETE
    -0.52
     Zinn
    -0.52
     magique
    -0.51
    POSITIVE LOGITS
     Scholar
    1.10
     SCHOLAR
    0.81
    Scholar
    0.76
     الاطلاع
    0.72
    ⓘ
    0.68
     scholar
    0.68
     للمعارف
    0.67
     שוליים
    0.66
    scholar
    0.65
    0.65
    Act Density 0.014%

    No Known Activations