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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    names of months, particularly those that have significance or narrative relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.91
    ascript
    -0.84
    ļéĨĴ
    -0.79
    ħĭ
    -0.78
    culosis
    -0.77
    olulu
    -0.75
    Interstitial
    -0.75
    plete
    -0.74
     suspic
    -0.74
    jriwal
    -0.71
    POSITIVE LOGITS
    nard
    0.96
    tag
    0.78
    sburg
    0.72
    urnal
    0.71
    oub
    0.71
    quist
    0.69
    hew
    0.67
    lene
    0.66
    flower
    0.65
     doom
    0.64
    Act Density 0.071%

    No Known Activations