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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs associated with judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluation and critique of media or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.60
    bill
    -0.59
    ingham
    -0.57
    eligible
    -0.56
    ajo
    -0.56
    ende
    -0.54
    avers
    -0.53
    ¿½
    -0.53
    apo
    -0.53
    isman
    -0.52
    POSITIVE LOGITS
     somew
    0.68
     carbs
    0.65
     spoilers
    0.61
     disclaimer
    0.60
     chronological
    0.58
     masturbation
    0.58
     multiplayer
    0.58
     wee
    0.56
     christ
    0.56
     monog
    0.55
    Act Density 1.113%

    No Known Activations