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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal and individual topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal health and individual rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seams
    -0.70
    ynt
    -0.68
    ÅĤ
    -0.66
    risome
    -0.65
    leck
    -0.64
    Ö¼
    -0.64
    Writer
    -0.62
    phase
    -0.61
    sea
    -0.60
    Reloaded
    -0.60
    POSITIVE LOGITS
     pronouns
    0.89
     pronoun
    0.79
     experiences
    0.68
     hobbies
    0.67
    atures
    0.67
     qui
    0.64
     preferences
    0.64
     electors
    0.63
    ombat
    0.62
    olitics
    0.61
    Act Density 0.169%

    No Known Activations