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

    Neuronpedia

    INDEX
    Explanations

    instances of tabular data or structured information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.82
     للمعارف
    -0.79
    sizeCache
    -0.77
     springfox
    -0.77
     MaterialApp
    -0.70
     ivelany
    -0.70
    ">//
    -0.68
     TextAppearance
    -0.65
    Autoritní
    -0.65
    RTEX
    -0.64
    POSITIVE LOGITS
    Sure
    0.80
     Saf
    0.72
     Sure
    0.71
    td
    0.69
     Fair
    0.66
    Safe
    0.66
    Fair
    0.64
    Saf
    0.62
     FAIR
    0.60
    Kor
    0.59
    Act Density 0.085%

    No Known Activations