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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural formatting elements within text

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

    Code, file paths, and hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    archaic spellings with ſ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.95
    ,
    -0.94
     (
    -0.92
     -
    -0.89
     A
    -0.88
     I
    -0.88
     –
    -0.85
     [
    -0.84
    ↵↵
    -0.84
     C
    -0.82
    POSITIVE LOGITS
    ſelf
    1.84
    ſelves
    1.80
     pleaſure
    1.77
     itſelf
    1.74
     myſelf
    1.65
     ་་
    1.61
     Anſ
    1.60
     Majefty
    1.58
     Efq
    1.58
     Reſ
    1.58
    Act Density 0.751%

    No Known Activations