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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.84
     Efq
    -0.77
     itſelf
    -0.70
     doubtnut
    -0.70
     demas
    -0.68
    ...}
    -0.66
    ſelf
    -0.65
    ěst
    -0.65
    ...')
    -0.65
     Dzi
    -0.64
    POSITIVE LOGITS
     +
    1.67
    ++++++++++++++++
    1.11
     +(
    1.04
     +=
    1.04
     +\
    1.04
     =
    1.02
    hitheatre
    0.98
     $+\
    0.93
     +
    0.92
    ContextCompat
    0.92
    Act Density 0.241%

    No Known Activations