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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high level of accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foy
    -0.14
    FromClass
    -0.14
    alet
    -0.14
    washer
    -0.14
    mdb
    -0.13
    _MUTEX
    -0.13
    ties
    -0.13
    eler
    -0.13
    peare
    -0.13
    -gnu
    -0.13
    POSITIVE LOGITS
     СÑĤÑĢана
    0.16
    ekler
    0.15
    ym
    0.14
    adesh
    0.14
    usch
    0.14
     fich
    0.14
    uan
    0.14
    imed
    0.13
     Vin
    0.13
    çݯ
    0.13
    Act Density 0.000%

    No Known Activations