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

    Neuronpedia

    INDEX
    Explanations

    Hebrew characters and words

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that appear to be non-standard or encoded text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.92
    essa
    -0.74
     Rapp
    -0.71
    eneg
    -0.69
    aturdays
    -0.69
    swick
    -0.67
     Osc
    -0.65
    itz
    -0.63
     sighting
    -0.63
    kef
    -0.62
    POSITIVE LOGITS
    ¤
    1.33
    ĵ
    1.30
    à¤
    1.26
    ļ
    1.22
    ¹
    1.20
    ¦
    1.20
    ķ
    1.19
    ¡
    1.17
    Ĺ
    1.15
    ¼
    1.14
    Act Density 0.004%

    No Known Activations