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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons using the word "than"

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving comparisons related to quantity or level thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Juda
    -0.72
     millenn
    -0.71
     largeDownload
    -0.65
    uploads
    -0.65
    taboola
    -0.64
    olitan
    -0.64
    uther
    -0.63
    Eye
    -0.62
    owe
    -0.62
     Palestin
    -0.61
    POSITIVE LOGITS
    average
    0.73
     1500
    0.71
    stellar
    0.68
     contiguous
    0.67
     Magicka
    0.66
     5000
    0.66
     XXX
    0.65
     1440
    0.64
     compensated
    0.63
    angular
    0.63
    Act Density 0.098%

    No Known Activations