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

    Neuronpedia

    INDEX
    Explanations

    abstract or scientific terminology related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.83
     Efq
    -0.65
     Houſe
    -0.63
     Anſ
    -0.61
     houſe
    -0.61
     Sist
    -0.61
     unw
    -0.60
    ſelves
    -0.59
    ſelf
    -0.58
     faſt
    -0.58
    POSITIVE LOGITS
     للمعارف
    0.84
     ddelweddau
    0.67
    findpost
    0.59
     righe
    0.59
     onBind
    0.58
     måde
    0.57
     fondi
    0.57
     piedi
    0.57
     cuerdas
    0.54
    Rüyada
    0.54
    Act Density 0.167%

    No Known Activations