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

    Neuronpedia

    INDEX
    Explanations

    scientific terms and concepts related to physics and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     myſelf
    -1.11
     Jefus
    -1.05
     themſelves
    -1.02
     pleaſure
    -1.00
     Majefty
    -0.97
    ſelf
    -0.93
     poffible
    -0.92
     Efq
    -0.90
    IntoConstraints
    -0.89
    POSITIVE LOGITS
     fiducia
    0.58
     المعيارى
    0.57
    -
    0.50
     or
    0.49
    aarrggbb
    0.48
     and
    0.46
    bootstrapcdn
    0.46
    ://
    0.45
     Tar
    0.44
     target
    0.44
    Act Density 1.970%

    No Known Activations