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

    Neuronpedia

    INDEX
    Explanations

    references to authors or contributors in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.99
     tranſ
    -0.98
     Anſ
    -0.98
     ſever
    -0.98
     pleaſure
    -0.96
     ſeveral
    -0.96
     faſt
    -0.96
     houſe
    -0.94
     reaſon
    -0.94
     purpoſe
    -0.94
    POSITIVE LOGITS
     et
    1.62
     Et
    1.08
     ET
    0.98
     للمعارف
    0.95
    Et
    0.93
    et
    0.92
     cetera
    0.81
     appelez
    0.80
     AttributeSet
    0.78
     puesta
    0.75
    Act Density 0.047%

    No Known Activations