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

    Neuronpedia

    INDEX
    Explanations

    instances of particular names or entities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances where the name "Josh" is mentioned

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    anwhile
    -0.72
     criminals
    -0.64
    ered
    -0.63
    ensional
    -0.61
    eering
    -0.61
    bath
    -0.61
    zsche
    -0.60
    clusively
    -0.59
    ertodd
    -0.59
    cers
    -0.58
    POSITIVE LOGITS
    awk
    1.11
    nikov
    1.07
    adow
    1.01
    ooter
    0.97
    ORTS
    0.95
    tml
    0.95
    ima
    0.94
    ttp
    0.93
    awks
    0.88
    oots
    0.88
    Act Density 0.019%

    No Known Activations