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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and the context surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovit
    -0.16
    owing
    -0.16
    heim
    -0.15
    erland
    -0.15
    izons
    -0.15
    readcr
    -0.15
    ứt
    -0.15
    Ñijм
    -0.15
    ade
    -0.15
    osal
    -0.15
    POSITIVE LOGITS
    ees
    0.21
    ys
    0.17
    392
    0.17
    ee
    0.17
    ulse
    0.15
    rech
    0.15
    avoid
    0.15
     spoken
    0.14
    ined
    0.14
    lsa
    0.14
    Act Density 0.018%

    No Known Activations