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

    Neuronpedia

    INDEX
    Explanations

    adjectives relating to personal characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal matters and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĤ
    -0.70
    risome
    -0.69
     seams
    -0.67
     Arrows
    -0.66
    phase
    -0.62
    д
    -0.61
    ynt
    -0.60
    Writer
    -0.59
    sterdam
    -0.58
    sea
    -0.58
    POSITIVE LOGITS
     pronouns
    0.83
     pronoun
    0.71
    £ı
    0.70
     hobbies
    0.66
    atures
    0.66
    ttle
    0.66
     UNCLASSIFIED
    0.66
    styles
    0.65
     identifiable
    0.64
     qui
    0.63
    Act Density 0.225%

    No Known Activations