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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ain
    -0.17
     arisen
    -0.16
    mailbox
    -0.16
    readcr
    -0.15
    emaker
    -0.15
     Ain
    -0.14
    richt
    -0.14
    å²
    -0.14
    laus
    -0.14
    ("")]↵
    -0.14
    POSITIVE LOGITS
    enek
    0.17
    igh
    0.15
    aket
    0.15
    alo
    0.15
    crets
    0.14
    umper
    0.14
    abouts
    0.14
    alion
    0.14
    ason
    0.14
    unto
    0.14
    Act Density 0.115%

    No Known Activations