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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating examples or illustrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lio
    -0.18
    ãĤ¥
    -0.16
    Å¡k
    -0.16
    azing
    -0.15
    readcr
    -0.15
    adlo
    -0.15
    zac
    -0.14
    ury
    -0.14
    ration
    -0.14
    urance
    -0.14
    POSITIVE LOGITS
    vez
    0.19
    ëį°
    0.17
    -Sah
    0.14
    itra
    0.14
    elves
    0.14
    es
    0.14
    iname
    0.14
     váºŃy
    0.14
    士
    0.14
    andom
    0.14
    Act Density 0.036%

    No Known Activations