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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes or terms that suggest exclusion or non-privilege

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivate
    -0.20
    ients
    -0.16
    aterangepicker
    -0.16
     uncert
    -0.14
    ansen
    -0.14
    oya
    -0.14
    tings
    -0.14
    ÑĨÑĮ
    -0.14
    acles
    -0.14
    sembles
    -0.14
    POSITIVE LOGITS
    linear
    0.17
    etheless
    0.15
    edly
    0.14
    Stop
    0.14
    .ast
    0.14
    rocket
    0.13
    ilibrium
    0.13
    profit
    0.13
     HOLDERS
    0.13
    astery
    0.13
    Act Density 0.024%

    No Known Activations