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

    Neuronpedia

    INDEX
    Explanations

    narratives involving transformation, possession, or manipulation of individuals

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

    turning evil or controlled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.60
    verwijspagina
    -0.42
     vVar
    -0.39
    př
    -0.38
     přek
    -0.38
     Geografía
    -0.38
    Geograf
    -0.37
    RTCK
    -0.37
    Билгалдахарш
    -0.36
    Begriffsklä
    -0.36
    POSITIVE LOGITS
     corrupted
    0.87
     transformed
    0.78
     infected
    0.75
     corrom
    0.75
     succumbed
    0.75
     becoming
    0.73
     succumb
    0.70
     transformation
    0.69
     contaminated
    0.68
     Becoming
    0.68
    Act Density 0.083%

    No Known Activations