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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mann
    -0.16
    amp
    -0.15
     mue
    -0.15
    amoto
    -0.14
    opoulos
    -0.14
    ammen
    -0.14
    etter
    -0.14
    ediator
    -0.14
    track
    -0.14
    hard
    -0.14
    POSITIVE LOGITS
     ******************************************************************************/↵↵
    0.16
    bol
    0.15
    ismic
    0.15
    bout
    0.15
    ĶåĽŀ
    0.14
    iggs
    0.14
    enheim
    0.14
    intptr
    0.14
    Ñħо
    0.14
     Wag
    0.13
    Act Density 0.050%

    No Known Activations