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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approval or positive evaluation

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate a subjective or personal experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chess
    -0.68
     Skydragon
    -0.67
     mathemat
    -0.66
     Alban
    -0.65
     pyramid
    -0.65
     trainers
    -0.64
     shelter
    -0.64
     mic
    -0.63
     ash
    -0.63
     Samar
    -0.63
    POSITIVE LOGITS
    ve
    1.24
    should
    1.20
    felt
    1.19
    re
    1.18
    ought
    1.15
    sure
    1.14
    sent
    1.13
    tre
    1.12
    shall
    1.11
    been
    1.11
    Act Density 0.301%

    No Known Activations