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

    Neuronpedia

    INDEX
    Explanations

    references to consent and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.08
    lette
    -0.07
    leston
    -0.07
    ì¶ķ
    -0.07
    vig
    -0.07
    alet
    -0.07
    erb
    -0.07
    kest
    -0.07
    áºŃy
    -0.07
    itecture
    -0.07
    POSITIVE LOGITS
    ably
    0.08
    able
    0.08
    IONS
    0.08
    ively
    0.07
    ive
    0.07
    ance
    0.07
    entially
    0.07
    aneous
    0.07
    454
    0.07
    ioneer
    0.06
    Act Density 0.004%

    No Known Activations