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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and computing, specifically focusing on terms related to programming languages and concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "aa" and similar patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schwarz
    -0.77
     Korean
    -0.73
     Schr
    -0.73
     Petraeus
    -0.71
     Jenner
    -0.70
     Plat
    -0.70
     Greenwald
    -0.67
     Soccer
    -0.66
     Koreans
    -0.66
     Huntington
    -0.66
    POSITIVE LOGITS
    aa
    1.23
    terness
    1.06
    aah
    0.99
    ibaba
    0.92
    aaa
    0.90
    ð
    0.88
    elta
    0.84
    uthor
    0.84
    asa
    0.82
    ldom
    0.81
    Act Density 0.005%

    No Known Activations