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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "I" and variations of it, indicating self-reference and personal experiences

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

    tomi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bard
    -0.41
    oader
    -0.41
    quard
    -0.40
    lardır
    -0.40
    irited
    -0.39
     LIRE
    -0.39
    pass
    -0.38
     tayang
    -0.38
    Oph
    -0.37
     Volkes
    -0.37
    POSITIVE LOGITS
     незавершена
    0.85
     CreateTagHelper
    0.67
     EconPapers
    0.60
    AndEndTag
    0.59
    StoryboardSegue
    0.56
    oa̍t
    0.54
     ویکی‌پدی
    0.54
     урна
    0.53
     Administrativna
    0.52
    localctx
    0.50
    Act Density 0.047%

    No Known Activations