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

    Neuronpedia

    INDEX
    Explanations

    references to rooms or spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </tfoot>
    -0.73
     Réponses
    -0.66
     ::=
    -0.64
    ]--;
    -0.64
    startAnimation
    -0.63
    batik
    -0.58
    ViewFeatures
    -0.57
     relève
    -0.57
     espirituales
    -0.57
     متعلقه
    -0.56
    POSITIVE LOGITS
     rooms
    1.13
    rooms
    1.08
     Room
    1.07
     Rooms
    1.04
     room
    1.02
     ROOM
    0.97
    Room
    0.95
    Rooms
    0.93
    room
    0.92
    ROOM
    0.91
    Act Density 0.107%

    No Known Activations