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

    Neuronpedia

    INDEX
    Explanations

    references to the "back" of objects or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    756
    -0.17
    peria
    -0.16
    ucc
    -0.15
    outh
    -0.14
    ogo
    -0.14
    uno
    -0.14
    ought
    -0.14
    atively
    -0.13
    ethod
    -0.13
    avax
    -0.13
    POSITIVE LOGITS
    hoe
    0.20
    side
    0.20
    seat
    0.20
    /front
    0.19
    NOWLED
    0.18
    country
    0.18
    slash
    0.18
    -end
    0.18
    ends
    0.18
    gam
    0.17
    Act Density 0.021%

    No Known Activations