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

    Neuronpedia

    INDEX
    Explanations

    variables and equations in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setAll
    -0.67
     możliwe
    -0.58
     Toten
    -0.57
    Thank
    -0.55
    ربعة
    -0.54
    OutOfRange
    -0.53
     shape
    -0.53
     måte
    -0.53
    The
    -0.52
     Trost
    -0.52
    POSITIVE LOGITS
     Jamb
    1.29
     Jot
    1.16
     JAS
    1.15
     J
    1.15
     jLabel
    1.14
     Jays
    1.14
     Jarvis
    1.13
     Jy
    1.13
     Jop
    1.11
     Joplin
    1.11
    Act Density 0.897%

    No Known Activations