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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical models and random variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "model," "functions," or "partition"

    np_acts-logits-general · gemini-2.0-flash

    statistical model associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &
    -0.52
     –
    -0.51
    ?
    -0.50
    ™
    -0.49
    ">'
    -0.48
     Don
    -0.48
    邦
    -0.47
     main
    -0.47
     -
    -0.46
    融
    -0.46
    POSITIVE LOGITS
    WithIOException
    1.05
     whoſe
    1.01
     Shaksp
    0.89
     Efq
    0.88
    حياته
    0.88
    ModelSerializer
    0.86
    InputBorder
    0.86
     uſ
    0.85
     Shakspeare
    0.85
     Eſ
    0.85
    Act Density 1.990%

    No Known Activations