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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or differences

    oai_token-act-pair · gpt-3.5-turbo

    words related to different forms of "pale."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duff
    -0.66
    ÄŁ
    -0.65
     awaited
    -0.64
    Hamilton
    -0.63
    gu
    -0.63
    AMES
    -0.62
     Darling
    -0.61
    swick
    -0.61
    ALLY
    -0.61
    GAN
    -0.61
    POSITIVE LOGITS
    haps
    0.94
    ebin
    0.85
    aea
    0.80
    athlon
    0.80
    umatic
    0.79
    lete
    0.77
    ysis
    0.77
    inters
    0.73
    olithic
    0.73
    asi
    0.71
    Act Density 0.051%

    No Known Activations