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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.73
    æ©
    -0.68
    ĸļ
    -0.66
    lance
    -0.65
    kamp
    -0.63
     Line
    -0.63
    charges
    -0.62
    file
    -0.62
    plex
    -0.62
    quin
    -0.61
    POSITIVE LOGITS
     necessarily
    0.88
     outright
    0.86
    eworthy
    0.84
    epad
    0.79
    acles
    0.76
     exactly
    0.74
    icably
    0.74
     entirely
    0.73
     remotely
    0.73
     adequately
    0.70
    Act Density 0.035%

    No Known Activations