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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and operations related to rounding and flooring values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OptionsMenu
    -0.48
    SequentialGroup
    -0.40
     våre
    -0.35
     تانيه
    -0.34
     ours
    -0.33
     géographique
    -0.33
     defaultstate
    -0.33
    WriteBarrier
    -0.32
     <<<<<<<<<<<<<<
    -0.32
    ณ์
    -0.32
    POSITIVE LOGITS
    ceil
    0.84
     ceil
    0.77
    round
    0.70
    floor
    0.69
    lfloor
    0.69
     rounding
    0.66
     Round
    0.66
     ROUND
    0.65
    Round
    0.65
     rounded
    0.65
    Act Density 0.245%

    No Known Activations