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

    Neuronpedia

    INDEX
    Explanations

    words related to upgrading and improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enhancing or improving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bered
    -0.78
     Unch
    -0.75
    erella
    -0.73
    pal
    -0.73
     Caption
    -0.71
    fried
    -0.68
    tering
    -0.68
    LESS
    -0.68
    cheat
    -0.65
    avery
    -0.64
    POSITIVE LOGITS
    grades
    0.98
    grading
    0.93
     upgrades
    0.90
    ments
    0.86
    graded
    0.83
     upgrade
    0.83
    xual
    0.82
     downgrade
    0.77
     depreciation
    0.77
     subscriptions
    0.75
    Act Density 0.020%

    No Known Activations