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

    Neuronpedia

    INDEX
    Explanations

    references to specific years or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å´
    -0.16
    leigh
    -0.14
    fg
    -0.14
    olumbia
    -0.14
     Reform
    -0.13
    Æ¡i
    -0.13
    oretical
    -0.13
    nt
    -0.13
    elo
    -0.13
    zl
    -0.13
    POSITIVE LOGITS
    s
    0.26
    sWith
    0.18
    ies
    0.18
    sik
    0.15
    swith
    0.15
    sı
    0.15
    serrat
    0.15
    sled
    0.15
    sand
    0.15
    -Ñħ
    0.15
    Act Density 0.034%

    No Known Activations