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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal restrictions and sanctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.79
     $_"
    -0.73
    IndentedString
    -0.72
    Abit
    -0.70
     estekak
    -0.68
     الحره
    -0.67
    astify
    -0.66
    __":
    -0.64
     INTERESAR
    -0.62
     Senna
    -0.61
    POSITIVE LOGITS
     kaik
    0.53
     EVERYTHING
    0.52
     toutes
    0.51
     apapun
    0.50
    一切
    0.50
     anything
    0.49
     everything
    0.48
     all
    0.48
     mọi
    0.47
     всеми
    0.46
    Act Density 0.567%

    No Known Activations