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

    Neuronpedia

    INDEX
    Explanations

    mentions of doors and their states or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.87
    ]--;
    -0.85
    .*")]
    -0.72
     AspNetCore
    -0.60
     HasFactory
    -0.58
    Anhalt
    -0.57
     aikaa
    -0.57
    Activités
    -0.54
    ftagPool
    -0.53
    いる
    -0.53
    POSITIVE LOGITS
    teps
    0.93
    🚪
    0.79
     doors
    0.78
    keeper
    0.75
     Doors
    0.70
     DOOR
    0.70
    bells
    0.69
    keepers
    0.69
    Doors
    0.68
     door
    0.67
    Act Density 0.058%

    No Known Activations