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

    Neuronpedia

    INDEX
    Explanations

    text that includes specific symbols or characters that serve as markers or separators within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of severe consequences, particularly relating to legal or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     diving
    -0.77
     experien
    -0.74
     compos
    -0.72
     attractions
    -0.71
     undet
    -0.71
     brass
    -0.71
     cons
    -0.71
    iors
    -0.70
     brill
    -0.70
     endeav
    -0.68
    POSITIVE LOGITS
    Comment
    1.06
    emphasis
    1.02
    Said
    0.92
    Posted
    0.89
    ONSORED
    0.88
    Pause
    0.88
    Clearly
    0.87
     ³³
    0.86
    Wikipedia
    0.86
    Pages
    0.85
    Act Density 0.241%

    No Known Activations