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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by possessive adjectives and nouns, related to personal achievements or goals

    oai_token-act-pair · gpt-3.5-turbo

    references to achieving personal or collective goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tabl
    -0.68
     nervously
    -0.64
    ways
    -0.64
     Tracks
    -0.63
     dudes
    -0.63
     newspapers
    -0.62
     tape
    -0.60
     Trave
    -0.59
     traces
    -0.59
    wi
    -0.59
    POSITIVE LOGITS
     immortality
    0.95
     milestones
    0.88
     milestone
    0.87
    thood
    0.87
     parity
    0.86
     fruition
    0.86
     feat
    0.84
     mastery
    0.83
     notoriety
    0.81
    omorphic
    0.80
    Act Density 0.128%

    No Known Activations