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

    Neuronpedia

    INDEX
    Explanations

    topics related to identity and representation

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

    Followed by prepositions indicating agency ("by", "oleh", "przez", etc.)

    np_acts-logits-general · gemini-2.0-flash

    agentive prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.72
    évaluateur
    -0.60
    GEBURTSDATUM
    -0.53
     tartalomajánló
    -0.53
    inSlope
    -0.49
    ANDUM
    -0.49
    ps
    -0.47
    GMENT
    -0.47
    PYX
    -0.46
    把自己
    -0.46
    POSITIVE LOGITS
     by
    1.75
     oleh
    1.71
     przez
    1.23
     توسط
    1.11
    by
    1.09
     pelos
    1.05
     пользователем
    1.00
     ידי
    0.97
     bởi
    0.97
     pela
    0.91
    Act Density 1.170%

    No Known Activations