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

    Neuronpedia

    INDEX
    Explanations

    items related to formal procedures or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     str
    -0.19
    ugh
    -0.15
     Juliet
    -0.14
    ota
    -0.14
    inion
    -0.14
    utherland
    -0.14
     Fly
    -0.13
     Motor
    -0.13
    ango
    -0.13
    osa
    -0.13
    POSITIVE LOGITS
    archical
    0.15
    گرد
    0.15
    kowski
    0.14
     Geh
    0.14
    ront
    0.14
    roat
    0.14
    ãĤ©
    0.14
    ÐIJÑĢÑħÑĸв
    0.13
    nia
    0.13
    ARRANT
    0.13
    Act Density 0.044%

    No Known Activations