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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions involving opinion and critique

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

    Followed by personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.04
     poffible
    -0.94
     purpoſe
    -0.91
     feveral
    -0.90
     myſelf
    -0.90
    ſelf
    -0.89
     Efq
    -0.86
     ſmall
    -0.84
     Diſ
    -0.84
     ſtate
    -0.83
    POSITIVE LOGITS
     he
    0.84
     they
    0.82
     you
    0.66
     she
    0.63
    They
    0.60
    帖最后由
    0.58
     He
    0.58
    He
    0.58
     we
    0.57
    DoubleQuotes
    0.55
    Act Density 0.208%

    No Known Activations