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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with a comma

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    ãĤ¶
    -0.65
    IU
    -0.65
    ORD
    -0.63
    ļéĨĴ
    -0.63
    olves
    -0.62
    Ô
    -0.61
    ords
    -0.61
     coverage
    -0.58
    APH
    -0.58
    POSITIVE LOGITS
     alas
    1.17
     uh
    0.90
     yeah
    0.87
     secondly
    0.79
     needless
    0.76
     moreover
    0.76
     yes
    0.75
     according
    0.73
     lest
    0.73
     unlike
    0.73
    Act Density 0.121%

    No Known Activations