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

    Neuronpedia

    INDEX
    Explanations

    references to different types of floors and their conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newVal
    -0.76
    ⓧ
    -0.72
     Königreich
    -0.70
    多い
    -0.69
    pidou
    -0.69
    sgn
    -0.69
     Ives
    -0.68
    เป
    -0.67
    acana
    -0.67
     Paesi
    -0.67
    POSITIVE LOGITS
     floor
    1.99
     floors
    1.92
     Floor
    1.86
     FLOOR
    1.82
    floor
    1.75
    Floor
    1.72
     Floors
    1.71
    FLOOR
    1.70
    floors
    1.63
     flooring
    1.46
    Act Density 0.031%

    No Known Activations