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

    Neuronpedia

    INDEX
    Explanations

    properties, functions, and impacts related to substances and their effects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tfrac
    -0.51
     Sah
    -0.48
     Ce
    -0.47
    AutoScaleMode
    -0.45
     pal
    -0.45
     Sa
    -0.45
    GOTREF
    -0.44
    trou
    -0.44
    Ce
    -0.43
    לפ
    -0.43
    POSITIVE LOGITS
     pleaſure
    0.94
    ſelf
    0.90
     ſtate
    0.82
     Répondre
    0.81
     itſelf
    0.81
    findpost
    0.80
     Houſe
    0.80
     Monfieur
    0.80
     houſe
    0.79
     Reſ
    0.78
    Act Density 0.175%

    No Known Activations