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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures related to numerical data or coding elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -0.96
     Theſe
    -0.95
     purpoſe
    -0.94
     Diſ
    -0.94
     pleaſure
    -0.87
     Chriftian
    -0.86
     houſe
    -0.85
     reaſon
    -0.85
     Anſ
    -0.84
     Reſ
    -0.84
    POSITIVE LOGITS
    homonymie
    0.66
    sizeCache
    0.55
    MathML
    0.53
    ordu
    0.53
     A
    0.50
    hicles
    0.49
    ym
    0.48
     Mol
    0.47
    stalt
    0.46
    enterio
    0.46
    Act Density 0.034%

    No Known Activations