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

    Neuronpedia

    INDEX
    Explanations

    references to formal documentation or procedural instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.01
    NUMX
    -0.89
     XNUMX
    -0.87
     myſelf
    -0.87
     Anſ
    -0.82
     faſt
    -0.79
     Mahomet
    -0.78
     Yah
    -0.78
     Hift
    -0.77
     depositphotos
    -0.76
    POSITIVE LOGITS
     hence
    0.80
     upto
    0.80
     Hence
    0.80
    upto
    0.78
     till
    0.78
    respective
    0.74
    Hence
    0.72
     irrespective
    0.71
    noOf
    0.70
     equipments
    0.69
    Act Density 1.309%

    No Known Activations