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

    Neuronpedia

    INDEX
    Explanations

    terms related to exclusivity or special access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilde
    -0.16
    ìĦľ
    -0.16
    rey
    -0.15
    esch
    -0.15
    orous
    -0.15
    acer
    -0.15
    estro
    -0.15
    ÑĩиÑĤ
    -0.15
    ug
    -0.14
    estation
    -0.14
    POSITIVE LOGITS
    ively
    0.28
    iveness
    0.21
    ities
    0.20
    ELY
    0.20
    /original
    0.18
    ely
    0.18
    -purpose
    0.18
    vely
    0.17
    ivity
    0.17
     exclus
    0.17
    Act Density 0.017%

    No Known Activations