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

    Neuronpedia

    INDEX
    Explanations

    negative signs or references to negative values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :");
    -0.73
    دانشنامهٔ
    -0.72
    \}.
    -0.66
    ?
    -0.66
    ობ
    -0.66
    LayoutStyle
    -0.66
     Roskov
    -0.65
    )");
    -0.65
    ?");
    -0.64
    sizePolicy
    -0.63
    POSITIVE LOGITS
     -
    2.61
     –
    1.69
     -"
    1.68
     -}
    1.61
     -\
    1.57
    {-
    1.53
     −
    1.47
     ‐
    1.47
     '-
    1.45
    >-</
    1.45
    Act Density 0.635%

    No Known Activations