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

    Neuronpedia

    INDEX
    Explanations

    unique tokens or identifiers from datasets or code snippets

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

    Special characters and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code or mathematical context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.04
    IntoConstraints
    -0.96
    出版年
    -0.92
     poffible
    -0.91
     occaf
    -0.87
     stanovnika
    -0.85
    GEBURTSDATUM
    -0.85
     raiſ
    -0.84
     itſelf
    -0.82
    IsMutable
    -0.82
    POSITIVE LOGITS
    [toxicity=0]
    1.20
     }^{*}$
    0.98
     *
    0.87
    *",
    0.85
     *}$
    0.83
     endblock
    0.80
    *)
    0.76
     *}
    0.75
     ')
    0.75
    *',
    0.74
    Act Density 0.020%

    No Known Activations