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

    Neuronpedia

    INDEX
    Explanations

    references to different types of floors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newVal
    -0.75
     Königreich
    -0.75
    多い
    -0.74
     acte
    -0.71
     sauvage
    -0.71
    เป
    -0.70
     pè
    -0.70
    eratops
    -0.70
    nbt
    -0.68
     kuat
    -0.68
    POSITIVE LOGITS
     floors
    1.50
     floor
    1.50
     Floor
    1.49
     FLOOR
    1.41
     Floors
    1.39
    FLOOR
    1.35
    Floor
    1.33
    floors
    1.33
    floor
    1.31
     flooring
    1.14
    Act Density 0.034%

    No Known Activations