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

    Neuronpedia

    INDEX
    Explanations

    references to roles and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of roles and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    role model limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBarButtonItem
    -0.64
    зулта
    -0.64
     للمعارف
    -0.61
    twimg
    -0.60
    ubblica
    -0.59
    GMENT
    -0.58
    OGND
    -0.58
    ihnachten
    -0.56
     صوتيه
    -0.56
    hips
    -0.55
    POSITIVE LOGITS
     played
    0.81
    playing
    0.76
     reversal
    0.75
     models
    0.75
     role
    0.75
    play
    0.72
     roles
    0.72
     ROLE
    0.70
    played
    0.70
     model
    0.68
    Act Density 0.021%

    No Known Activations