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

    Neuronpedia

    INDEX
    Explanations

    names of authors or researchers affiliated with scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utto
    -0.18
     as
    -0.15
    aran
    -0.15
    -0.15
    ...
    -0.15
    esty
    -0.15
    Playable
    -0.15
    ↵
    -0.15
     ver
    -0.14
    /
    -0.14
    POSITIVE LOGITS
    lili
    0.18
    allen
    0.17
     Lv
    0.17
    jun
    0.16
    SSERT
    0.16
    lei
    0.16
    (State
    0.16
     Fan
    0.15
     X
    0.15
    Jun
    0.15
    Act Density 0.073%

    No Known Activations