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

    Neuronpedia

    INDEX
    Explanations

    HTML code that includes specific attributes like `'` followed by `=`

    oai_token-act-pair · gpt-3.5-turbo

    HTML or XML attribute assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cay
    -0.68
     sche
    -0.66
     Saf
    -0.65
     stash
    -0.65
    mentioned
    -0.64
    ITH
    -0.64
     Baal
    -0.62
     conceal
    -0.62
    sche
    -0.61
     written
    -0.60
    POSITIVE LOGITS
    =\"
    1.09
    ļéĨĴ
    0.92
    agonists
    0.86
     Cosponsors
    0.85
    ":["
    0.80
     Skydragon
    0.78
    umbnails
    0.76
    kinson
    0.76
    ombat
    0.75
    ĪĴ
    0.75
    Act Density 0.000%

    No Known Activations