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

    Neuronpedia

    INDEX
    Explanations

    terms associated with conspiracy theories and references to power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.78
    quartile
    -0.70
    endpush
    -0.69
     '\\;'
    -0.68
     poffe
    -0.68
    opedic
    -0.68
    enterOuterAlt
    -0.67
    ільки
    -0.65
     GOLF
    -0.65
     ſch
    -0.63
    POSITIVE LOGITS
     healing
    0.57
    Portail
    0.52
     Healing
    0.50
    Hol
    0.49
     ~
    0.49
    yim
    0.47
    ).]
    0.47
     Leitung
    0.46
    Gaia
    0.46
    healing
    0.45
    Act Density 0.678%

    No Known Activations