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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or indecision

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

    So you

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of the speaker (first-person "I"/"I'm" and similar self-references).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.59
    存于互联网档案馆
    -0.55
     Roskov
    -0.54
     ProtoMessage
    -0.54
    Personendaten
    -0.53
    enterOuterAlt
    -0.50
     doInBackground
    -0.49
     Signalez
    -0.48
    awakeFromNib
    -0.47
    +#+
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.45
    long
    0.37
    ONOMY
    0.37
    ACIONAL
    0.36
     Sten
    0.36
     gustaría
    0.34
    onomy
    0.34
    Bill
    0.34
    rup
    0.34
    rspec
    0.34
    Act Density 0.318%

    No Known Activations