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

    Neuronpedia

    INDEX
    Explanations

    substrings following a pattern of slashes and names with varying activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the "REUTERS/" marker indicating news sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prol
    -0.77
    worms
    -0.73
     beetles
    -0.72
     worms
    -0.72
     idol
    -0.70
     verbs
    -0.69
     infertility
    -0.68
     sooner
    -0.67
    ĪĴ
    -0.65
     snakes
    -0.65
    POSITIVE LOGITS
    File
    0.99
    AFP
    0.94
    Getty
    0.93
    David
    0.93
    Mike
    0.90
    Jim
    0.89
    Flickr
    0.88
    Rick
    0.87
    Brend
    0.87
    Jonathan
    0.87
    Act Density 0.026%

    No Known Activations