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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.82
     esternos
    -0.73
    AnimationsModule
    -0.72
    UserScript
    -0.71
     चीज़ों
    -0.71
     للمعارف
    -0.69
     виправивши
    -0.69
    ftagPool
    -0.68
     صوتيه
    -0.67
    ########.
    -0.67
    POSITIVE LOGITS
     tør
    0.57
     empêche
    0.54
     băr
    0.53
    cluye
    0.53
    Mitochond
    0.51
     now
    0.50
     Catawiki
    0.50
     nothing
    0.50
     foncé
    0.49
    mandala
    0.48
    Act Density 0.323%

    No Known Activations