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

    Neuronpedia

    INDEX
    Explanations

    terms related to identity, verification, and existential themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    くださった
    -0.58
     Schot
    -0.54
     least
    -0.49
     MacGregor
    -0.48
     stata
    -0.48
     نبود
    -0.47
     گذاشت
    -0.47
     stato
    -0.46
    Ārējās
    -0.46
    тости
    -0.45
    POSITIVE LOGITS
    MergeFrom
    0.73
    躇
    0.65
    kloped
    0.64
     AttributeSet
    0.64
    gdx
    0.63
    pidou
    0.63
    tanleria
    0.62
     defaultstate
    0.61
    prüche
    0.61
    AsUp
    0.60
    Act Density 0.309%

    No Known Activations