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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to personal characteristics and behaviors, as well as suggestions or commands for improvement

    oai_token-act-pair · gpt-3.5-turbo

    descriptors and traits related to emotional and social characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agher
    -0.67
    Ô
    -0.66
     Purg
    -0.62
    antha
    -0.60
    ciation
    -0.59
    blem
    -0.59
    è£ħ
    -0.59
    PIN
    -0.59
    BuyableInstoreAndOnline
    -0.58
    ruction
    -0.57
    POSITIVE LOGITS
     minded
    1.13
     thinkers
    1.09
     towards
    1.07
     toward
    1.00
     learners
    0.95
     discipl
    0.87
     stewards
    0.84
     personalities
    0.83
     thinker
    0.82
     defensively
    0.81
    Act Density 0.217%

    No Known Activations