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

    Neuronpedia

    INDEX
    Explanations

    actions indicative of notable events or changes in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daly
    -0.17
    tery
    -0.17
    APE
    -0.14
    atchet
    -0.14
    EFR
    -0.14
     Paz
    -0.14
    ISIS
    -0.14
    uder
    -0.14
    463
    -0.13
     pol
    -0.13
    POSITIVE LOGITS
    ãģŁãģ¡ãģ¯
    0.15
    imore
    0.15
    achuset
    0.15
    oại
    0.15
     (++
    0.14
    acket
    0.14
    (',',$
    0.14
    ìĬ¤íĭ°
    0.14
    avou
    0.13
    ummings
    0.13
    Act Density 0.759%

    No Known Activations