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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate additional comments or observations about topics discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.81
     myſelf
    -0.77
     intptr
    -0.76
     Majefty
    -0.76
     sumpay
    -0.75
     fevere
    -0.73
     Anſ
    -0.71
     Reſ
    -0.71
     ويكيميديا
    -0.71
     faſt
    -0.70
    POSITIVE LOGITS
    Also
    0.78
     Also
    0.76
     also
    0.72
     επίσης
    0.70
    also
    0.70
    Additionally
    0.63
     también
    0.63
    Another
    0.63
     Another
    0.60
     também
    0.58
    Act Density 0.461%

    No Known Activations