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

    Neuronpedia

    INDEX
    Explanations

    variations of ASCII art

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of symbolic representations or formatting elements in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grey
    -0.90
    Gal
    -0.85
     Lebanese
    -0.84
     Gard
    -0.82
    Grey
    -0.81
     Yemeni
    -0.80
     Gal
    -0.74
     McGill
    -0.74
     Senegal
    -0.73
     Cant
    -0.73
    POSITIVE LOGITS
     __
    2.49
    init
    1.53
     init
    1.44
    __
    1.44
     Vij
    1.30
     /*
    1.21
    /*
    1.20
     racket
    1.18
     /**
    1.18
    )(
    1.11
    Act Density 0.056%

    No Known Activations