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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iston
    -0.16
    iming
    -0.15
    hard
    -0.15
    holder
    -0.14
    erator
    -0.14
    ãĥ§
    -0.14
    idget
    -0.14
    eration
    -0.14
    iversit
    -0.13
    å£
    -0.13
    POSITIVE LOGITS
    lassian
    0.18
    rophy
    0.18
    anas
    0.18
    /by
    0.18
    asha
    0.17
    tempts
    0.17
    sha
    0.17
    temps
    0.17
    macen
    0.16
    -home
    0.16
    Act Density 0.258%

    No Known Activations