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

    Neuronpedia

    INDEX
    Explanations

    cryptic messages encoded in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    elements related to webpages or internet content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     misunder
    -0.74
    uten
    -0.71
     nodd
    -0.70
     princ
    -0.69
     disadvant
    -0.67
     destro
    -0.67
     obser
    -0.66
     preval
    -0.66
     reluct
    -0.64
     plent
    -0.63
    POSITIVE LOGITS
    <|endoftext|>
    1.38
     Subscribe
    0.91
     »
    0.83
     Related
    0.74
    "}],"
    0.69
     Logged
    0.67
     âĹı
    0.67
    ↵↵
    0.66
     Apply
    0.65
     Author
    0.65
    Act Density 0.034%

    No Known Activations