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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meas
    -0.16
     Piet
    -0.16
     measurable
    -0.14
    ìĮ
    -0.14
     Buen
    -0.13
     Sa
    -0.13
     mø
    -0.13
     Pew
    -0.13
     Os
    -0.13
     Taj
    -0.13
    POSITIVE LOGITS
    floor
    0.26
     floor
    0.25
     div
    0.22
    -floor
    0.22
    Floor
    0.21
    Div
    0.20
     Floor
    0.20
     ceil
    0.20
     Div
    0.20
    _floor
    0.20
    Act Density 0.099%

    No Known Activations