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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operations related to calculus and physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brice
    -0.54
    ستی
    -0.51
     Pape
    -0.50
     tarts
    -0.49
    Richardson
    -0.49
     glasses
    -0.48
     plagio
    -0.48
    GoogleApiClient
    -0.48
    Tamp
    -0.47
     prototypes
    -0.47
    POSITIVE LOGITS
    _{\
    1.28
     _{\
    0.89
    IntoConstraints
    0.87
    _\
    0.86
     فريبيس
    0.84
    }_{\
    0.83
     $_{\
    0.77
    )_{\
    0.73
    \{\\
    0.71
     }_{\
    0.70
    Act Density 0.978%

    No Known Activations