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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [âĢ¦]↵↵
    -0.18
     [âĢ¦]
    -0.17
     âĢIJ
    -0.16
     ï
    -0.16
     [âĢ¦
    -0.15
    [,]
    -0.15
     ÂŃ
    -0.15
    âĢIJ
    -0.13
    âĢ¦↵↵
    -0.13
     âĢ
    -0.13
    POSITIVE LOGITS
    unma
    0.15
    ÃĤ
    0.15
    igham
    0.15
     arrang
    0.14
    acades
    0.14
     excer
    0.14
    erli
    0.14
    ılıģıyla
    0.14
    onse
    0.14
    hev
    0.14
    Act Density 0.594%

    No Known Activations