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

    Neuronpedia

    INDEX
    Explanations

    references to doors and doorsteps in various contexts

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

    door and doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.41
     Tch
    -0.40
     combineReducers
    -0.38
     Blackjack
    -0.38
     半袖
    -0.37
     jaki
    -0.36
    ızlık
    -0.36
     Bate
    -0.36
     missp
    -0.36
     Thatcher
    -0.35
    POSITIVE LOGITS
    Door
    1.74
     Door
    1.73
    door
    1.68
     DOOR
    1.60
     door
    1.59
    DOOR
    1.31
     Doors
    1.22
    doors
    1.18
     doors
    1.17
    Doors
    1.14
    Act Density 0.007%

    No Known Activations