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

    Neuronpedia

    INDEX
    Explanations

    words associated with various issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    munition
    -0.16
    otel
    -0.15
    terra
    -0.15
    /doc
    -0.15
    textInput
    -0.14
    ApplicationBuilder
    -0.14
    ëŁī
    -0.13
    istar
    -0.13
     ÎĶή
    -0.13
    aths
    -0.13
    POSITIVE LOGITS
     are
    0.18
     is
    0.17
     comes
    0.17
    iam
    0.16
    reb
    0.15
     came
    0.14
     gets
    0.14
     will
    0.14
     appears
    0.14
     happens
    0.14
    Act Density 0.338%

    No Known Activations