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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating durations or periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.20
     åĭ
    -0.17
    ikt
    -0.17
    oka
    -0.16
    lict
    -0.14
    jah
    -0.14
    icha
    -0.14
    ewan
    -0.14
    ighet
    -0.14
    èİī
    -0.13
    POSITIVE LOGITS
    ypes
    0.16
    duk
    0.15
    rale
    0.15
    tement
    0.15
    utz
    0.15
    ãĥ¼ãĥ«ãĥī
    0.14
    estring
    0.14
     FORMAT
    0.14
    ëĵĿ
    0.14
     баÑĤÑĮкÑĸв
    0.14
    Act Density 0.045%

    No Known Activations