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

    Neuronpedia

    INDEX
    Explanations

    references to floors and levels within various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     newVal
    -0.77
     Paesi
    -0.70
    mite
    -0.69
     SUBST
    -0.69
    Sant
    -0.68
    Punt
    -0.68
     Apre
    -0.68
     preghi
    -0.67
     sauvage
    -0.66
     Königreich
    -0.66
    POSITIVE LOGITS
     Floors
    1.39
     floors
    1.38
     Floor
    1.36
    FLOOR
    1.34
     FLOOR
    1.33
     floor
    1.32
    floors
    1.28
    Floor
    1.22
    floor
    1.16
     flooring
    1.09
    Act Density 0.006%

    No Known Activations