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

    Neuronpedia

    INDEX
    Explanations

    the word "at" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.68
    ÄŁ
    -0.68
    jri
    -0.67
    schild
    -0.64
    eur
    -0.63
    Ãį
    -0.62
    士
    -0.62
     Dj
    -0.61
    姫
    -0.60
    èĪ
    -0.60
    POSITIVE LOGITS
    keye
    0.74
    icle
    0.68
    isphere
    0.65
    neys
    0.64
    ting
    0.63
    bread
    0.63
    icles
    0.62
    erman
    0.61
    tern
    0.60
    storm
    0.60
    Act Density 0.125%

    No Known Activations