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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lump
    -0.72
     Gators
    -0.71
     wart
    -0.71
     Tall
    -0.69
     Turtles
    -0.68
     Bengal
    -0.68
    ugg
    -0.68
     Brow
    -0.67
    hawks
    -0.67
     Dynam
    -0.67
    POSITIVE LOGITS
    ×Ļ×
    2.03
    ×ķ
    1.91
    ×
    1.90
    ×Ļ
    1.88
    ש
    1.81
    ×IJ
    1.80
    ׾
    1.79
    ×ŀ
    1.79
    ר
    1.78
    ×Ķ
    1.74
    Act Density 0.011%

    No Known Activations