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

    Neuronpedia

    INDEX
    Explanations

    contextual references and mathematical notations related to evaluations and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.59
     “
    -0.48
    ...
    -0.47
    ->
    -0.45
     "
    -0.44
    거나
    -0.44
     
    -0.42
     V
    -0.39
    <?>
    -0.39
    tól
    -0.39
    POSITIVE LOGITS
     مشين
    0.87
    tagHelperRunner
    0.86
    SharedCtor
    0.83
     itſelf
    0.82
     myſelf
    0.78
     alike
    0.75
    +#+#
    0.73
     ―――――
    0.72
    Personendaten
    0.72
     ſind
    0.71
    Act Density 0.595%

    No Known Activations