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

    Neuronpedia

    INDEX
    Explanations

    references to maximum values or comparisons that imply limits or thresholds

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Geplaatst
    -1.18
    windowFixed
    -0.98
     purpoſe
    -0.96
     leaſt
    -0.95
    Rhestr
    -0.91
     myſelf
    -0.90
    OGND
    -0.90
    ]();
    -0.90
     ſeveral
    -0.87
     ſtate
    -0.85
    POSITIVE LOGITS
     Dana
    0.58
    es
    0.58
    al
    0.58
    ax
    0.57
    o
    0.57
    ness
    0.57
    ة
    0.56
    ビック
    0.55
     общества
    0.54
    x
    0.54
    Act Density 0.014%

    No Known Activations