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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is being described or quoted

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include descriptions and quotations from various individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.63
     ``(
    -0.60
     reproduction
    -0.58
     RELEASE
    -0.57
     Wave
    -0.55
     {"
    -0.55
     Martian
    -0.52
    caps
    -0.52
    "}],"
    -0.52
    dayName
    -0.51
    POSITIVE LOGITS
     by
    1.07
     extensively
    0.99
     favorably
    0.98
     repeatedly
    0.87
     unfairly
    0.85
     as
    0.83
     controvers
    0.79
     negatively
    0.78
     unanimously
    0.76
     harshly
    0.75
    Act Density 0.184%

    No Known Activations