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

    Neuronpedia

    INDEX
    Explanations

    the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tte
    -0.16
    iter
    -0.15
    iting
    -0.15
    tin
    -0.15
    ç©´
    -0.14
    cpt
    -0.14
    ayo
    -0.14
    ÄĽj
    -0.14
     Malk
    -0.14
    allee
    -0.13
    POSITIVE LOGITS
    cher
    0.18
     Siz
    0.17
    fern
    0.16
    оÑĢÑıд
    0.15
    lsru
    0.15
    pire
    0.14
    arer
    0.14
    /met
    0.14
     borderline
    0.14
     anymore
    0.13
    Act Density 0.011%

    No Known Activations