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

    Neuronpedia

    INDEX
    Explanations

    text related to reports, news, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    formal or official statements and reports, particularly those pertaining to legal or authoritative matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zion
    -0.61
    proc
    -0.58
     Entered
    -0.57
     Sovere
    -0.56
    ãĤ¯
    -0.55
     favourable
    -0.54
     colonization
    -0.54
     coh
    -0.54
    Cor
    -0.53
    fac
    -0.53
    POSITIVE LOGITS
     also
    0.76
     additionally
    0.75
     furthermore
    0.68
     ALSO
    0.66
    urai
    0.65
    llah
    0.64
    ohm
    0.64
     smelled
    0.63
     fixme
    0.62
    DragonMagazine
    0.62
    Act Density 0.908%

    No Known Activations