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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mlin
    -0.15
     settled
    -0.14
    ucken
    -0.14
    chner
    -0.14
    ilm
    -0.14
    razione
    -0.14
    anke
    -0.13
    ãĤ¦ãĥĪ
    -0.13
    ancers
    -0.13
    hood
    -0.13
    POSITIVE LOGITS
    inho
    0.15
    Meter
    0.15
    .utc
    0.15
    arding
    0.15
    warts
    0.14
     Martins
    0.14
    URT
    0.14
    lander
    0.14
    ä¸ĺ
    0.14
    .unit
    0.13
    Act Density 0.028%

    No Known Activations