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

    Neuronpedia

    INDEX
    Explanations

    terms related to organizational or administrative activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structures and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.65
    Ô
    -0.61
     diverse
    -0.60
    rown
    -0.59
     Contrast
    -0.59
    ãĤ¢ãĥ«
    -0.59
    incinn
    -0.59
    okin
    -0.59
    è¦ļéĨĴ
    -0.58
    ãĥ´
    -0.57
    POSITIVE LOGITS
    finals
    0.72
     aisle
    0.68
    eers
    0.66
     fiasco
    0.63
    inals
    0.62
     debacle
    0.62
    ariat
    0.62
     onwards
    0.61
    aires
    0.61
     brigade
    0.60
    Act Density 0.413%

    No Known Activations