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

    Neuronpedia

    INDEX
    Explanations

    the letter "C" followed by other specific letters in a text

    oai_token-act-pair · gpt-3.5-turbo

    specific letters, symbols, and words that indicate unique identifiers or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dise
    -0.91
     Raz
    -0.88
     Dickinson
    -0.83
     dime
    -0.82
     Iz
    -0.81
     Ivy
    -0.79
     Ezra
    -0.79
     Rig
    -0.78
     Dh
    -0.78
     Crane
    -0.78
    POSITIVE LOGITS
     Mun
    0.95
    mun
    0.93
    bil
    0.83
    atur
    0.83
    atalie
    0.80
     Blair
    0.79
    970
    0.78
    ala
    0.77
    ela
    0.76
     Hezbollah
    0.75
    Act Density 0.457%

    No Known Activations