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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     im
    -0.59
     az
    -0.57
     get
    -0.57
     zu
    -0.56
     in
    -0.56
     c
    -0.54
     to
    -0.54
     and
    -0.54
     M
    -0.52
     m
    -0.51
    POSITIVE LOGITS
     Majefty
    1.48
     myſelf
    1.48
     Monfieur
    1.48
    ſelf
    1.47
     itſelf
    1.44
     Efq
    1.38
    ſelves
    1.37
     Theſe
    1.35
     Jefus
    1.34
     pleaſure
    1.30
    Act Density 1.666%

    No Known Activations