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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML/XML tag-like structures and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hume
    -0.66
    姫
    -0.65
     wiret
    -0.65
     whistle
    -0.65
    odes
    -0.64
     fortun
    -0.64
     Hastings
    -0.63
     Miko
    -0.62
     warrant
    -0.61
    oms
    -0.61
    POSITIVE LOGITS
    ><
    1.14
    wcsstore
    0.98
    soever
    0.86
    anguage
    0.80
    "><
    0.79
     ><
    0.79
    !--
    0.76
    netic
    0.76
    input
    0.76
    fill
    0.73
    Act Density 0.007%

    No Known Activations