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

    Neuronpedia

    INDEX
    Explanations

    references to the pronoun "it" and similar indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     to
    -0.63
     “
    -0.59
     up
    -0.59
     in
    -0.56
     more
    -0.55
    ступил
    -0.54
     far
    -0.53
     
    -0.53
     impress
    -0.52
    abos
    -0.51
    POSITIVE LOGITS
     purpoſe
    0.84
     nakalista
    0.83
     Majefty
    0.83
     fubject
    0.81
     Houſe
    0.80
     pleaf
    0.80
    Obrázky
    0.79
    httphttps
    0.79
     "..\..\
    0.78
     Darauf
    0.77
    Act Density 0.047%

    No Known Activations