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

    Neuronpedia

    INDEX
    Explanations

    phrases related to architectural features and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .wik
    -0.15
     sabot
    -0.14
    rq
    -0.14
    urtle
    -0.14
    880
    -0.14
    룰
    -0.13
    Studio
    -0.13
    amedi
    -0.13
    attr
    -0.13
     decided
    -0.13
    POSITIVE LOGITS
     fue
    0.31
     était
    0.27
     was
    0.27
     бÑĭла
    0.25
    'était
    0.23
     бÑĭл
    0.23
    Was
    0.21
    _was
    0.21
     foi
    0.21
     Was
    0.21
    Act Density 0.118%

    No Known Activations