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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to analysis, investigation, or exploration, including questions, answers, clips, percentages, scenes, effects, pieces, methods, levels, stories, applications, patterns, instructions, penalties, gains, and others

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inquiry and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    votes
    -0.75
    Motion
    -0.71
    nant
    -0.70
    ALLY
    -0.68
    zi
    -0.66
    lette
    -0.64
    Adds
    -0.64
    DonaldTrump
    -0.60
    FLAG
    -0.60
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.59
    POSITIVE LOGITS
    etting
    1.06
    mith
    1.05
    etter
    1.02
     are
    1.01
     aren
    0.99
     weren
    0.98
    afety
    0.92
     were
    0.89
    cape
    0.88
     vary
    0.86
    Act Density 0.352%

    No Known Activations