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

    Neuronpedia

    INDEX
    Explanations

    words related to official statements or documented concerns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cum
    -0.80
    ãĤ´ãĥ³
    -0.80
    udder
    -0.76
    ãĤ´
    -0.72
    ?,
    -0.70
    android
    -0.69
    pless
    -0.68
     aka
    -0.67
    bg
    -0.67
    worn
    -0.66
    POSITIVE LOGITS
    resa
    1.26
    oret
    1.24
     notion
    1.15
     idea
    1.11
     biggest
    1.09
     reason
    1.08
     implication
    1.07
     intention
    1.07
     purpose
    1.06
     fact
    1.04
    Act Density 0.201%

    No Known Activations