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

    Neuronpedia

    INDEX
    Explanations

    references to minimum and maximum values or thresholds in settings and computations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _minor
    -0.17
     Mister
    -0.14
    Minor
    -0.14
     Mush
    -0.14
     Moss
    -0.14
    å¿
    -0.14
    алÑĥ
    -0.14
    Ĥ¨
    -0.13
     Mineral
    -0.13
     Minority
    -0.13
    POSITIVE LOGITS
     Max
    1.32
     max
    1.23
    Max
    1.19
    max
    1.11
    _max
    1.06
     MAX
    1.05
    -max
    1.02
    .max
    0.97
    MAX
    0.96
    .Max
    0.96
    Act Density 0.093%

    No Known Activations