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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases indicating a following statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the acknowledgment or citation of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elled
    -0.76
     Editors
    -0.64
    prus
    -0.64
    vous
    -0.64
    pins
    -0.62
    cat
    -0.59
    eatured
    -0.59
     Roads
    -0.59
    tele
    -0.59
    ARDS
    -0.58
    POSITIVE LOGITS
    itivity
    0.80
     caveats
    0.79
    lihood
    0.77
     hindsight
    0.71
     aside
    0.69
    ifference
    0.69
     anecd
    0.69
     respectfully
    0.68
     caveat
    0.68
    iments
    0.66
    Act Density 0.032%

    No Known Activations