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

    Neuronpedia

    INDEX
    Explanations

    terms related to mandates and regulatory requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ting
    -0.18
    angel
    -0.18
    adlo
    -0.17
    utions
    -0.17
    endale
    -0.16
    endez
    -0.16
    berman
    -0.16
    æľĭ
    -0.16
    bands
    -0.15
    çİĩ
    -0.15
    POSITIVE LOGITS
    wagon
    0.22
    ishments
    0.20
    eur
    0.19
    ahl
    0.18
    over
    0.18
    eb
    0.18
    wich
    0.18
    olph
    0.18
    orf
    0.17
    ev
    0.17
    Act Density 0.195%

    No Known Activations