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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asser
    -0.17
    stad
    -0.16
    stin
    -0.15
    ŀ
    -0.14
     sap
    -0.14
    омен
    -0.14
    NotFoundError
    -0.14
     Bits
    -0.14
    FAQ
    -0.14
     darm
    -0.13
    POSITIVE LOGITS
    iche
    0.16
    urdu
    0.14
    aro
    0.14
    orial
    0.14
     khá»ıe
    0.13
     (~(
    0.13
    adoo
    0.13
    OGRAPH
    0.13
    .decorate
    0.13
    ray
    0.13
    Act Density 0.077%

    No Known Activations