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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters or elements related to a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTTON
    -0.17
    rung
    -0.16
     actionTypes
    -0.16
    IFF
    -0.15
    ffen
    -0.15
     ActionTypes
    -0.15
    ubu
    -0.14
    vou
    -0.14
     Ellison
    -0.14
     bek
    -0.14
    POSITIVE LOGITS
    491
    0.18
    uhl
    0.16
    dale
    0.16
    leta
    0.14
    ulls
    0.14
    plate
    0.14
     corpor
    0.14
    opa
    0.13
    termin
    0.13
    **/↵↵
    0.13
    Act Density 0.003%

    No Known Activations