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

    Neuronpedia

    INDEX
    Explanations

    references to annual reviews and reflections on the past year's events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.16
    udden
    -0.16
    istar
    -0.14
    AIT
    -0.14
    ida
    -0.14
    uddenly
    -0.14
    arken
    -0.13
    isÃŃ
    -0.13
     RESERVED
    -0.13
    ania
    -0.13
    POSITIVE LOGITS
    _MACRO
    0.14
    ning
    0.14
    andler
    0.13
     polar
    0.13
    pio
    0.13
    lou
    0.13
    chw
    0.13
    ringe
    0.13
    etty
    0.13
     personally
    0.13
    Act Density 0.082%

    No Known Activations