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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dedication or commitments to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.16
    kins
    -0.15
    ulse
    -0.15
    ADS
    -0.14
    orer
    -0.14
    keit
    -0.13
    .misc
    -0.13
    çIJ´
    -0.13
    yen
    -0.13
    */
    -0.13
    POSITIVE LOGITS
    /compiler
    0.15
    ded
    0.15
     Siz
    0.14
     Mog
    0.14
    Touches
    0.14
    ednou
    0.14
    atures
    0.14
    OUN
    0.14
    MBOL
    0.14
    inear
    0.13
    Act Density 0.021%

    No Known Activations