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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "consent" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.84
    mania
    -0.73
    Lens
    -0.72
    gaard
    -0.69
    GPU
    -0.68
    vae
    -0.68
    nas
    -0.66
    tin
    -0.64
     Feld
    -0.60
    biz
    -0.59
    POSITIVE LOGITS
     decree
    0.99
     consent
    0.97
     decre
    0.86
    ignt
    0.85
     Consent
    0.81
    ible
    0.78
    ing
    0.76
    ajor
    0.74
    orative
    0.74
    ibility
    0.74
    Act Density 0.032%

    No Known Activations