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

    Neuronpedia

    INDEX
    Explanations

    formal language related to accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to achievements and accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odynamic
    -0.69
    othing
    -0.68
    oxin
    -0.67
    pper
    -0.66
    esthetic
    -0.66
    trop
    -0.66
    ondo
    -0.66
    ned
    -0.66
    sey
    -0.63
    creen
    -0.62
    POSITIVE LOGITS
     accomplishment
    1.17
     achievement
    1.15
     achievements
    1.11
     achie
    1.03
     attainment
    1.03
     feats
    1.02
     Achievement
    1.01
    rious
    0.98
     accomplishments
    0.98
     accomplished
    0.98
    Act Density 0.046%

    No Known Activations