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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udy
    -0.15
    pins
    -0.14
    OWN
    -0.14
    æīį
    -0.13
    ras
    -0.13
     Brut
    -0.13
    omy
    -0.13
    âĬ
    -0.13
     decade
    -0.13
     lÃŃ
    -0.13
    POSITIVE LOGITS
    shima
    0.16
    incy
    0.15
    bourg
    0.14
     mont
    0.14
    ço
    0.14
    icular
    0.14
     trx
    0.13
    دÙĨ
    0.13
    änge
    0.13
    mmas
    0.13
    Act Density 0.077%

    No Known Activations