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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.86
    bia
    -0.76
    Else
    -0.75
    igen
    -0.74
    Journal
    -0.72
    DNA
    -0.71
    Pand
    -0.70
    hift
    -0.70
    æĸ
    -0.69
    igon
    -0.69
    POSITIVE LOGITS
     ejected
    0.71
    akespe
    0.65
     Dres
    0.64
     clipboard
    0.62
     Avenger
    0.62
     Pam
    0.61
    vertisement
    0.61
    $$$$
    0.60
     Shades
    0.60
     reclaimed
    0.59
    Act Density 0.000%

    No Known Activations