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

    Neuronpedia

    INDEX
    Explanations

    specific city names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character '´' and references to "Yang."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.86
    perture
    -0.77
    DAQ
    -0.76
     millenn
    -0.72
    iaries
    -0.72
    NRS
    -0.70
    alty
    -0.69
    iciency
    -0.67
    ciating
    -0.66
     Rouhani
    -0.66
    POSITIVE LOGITS
    ãĤ¡
    1.03
    lda
    0.83
    ossus
    0.80
    onel
    0.78
    ogen
    0.76
    ogue
    0.74
    gren
    0.74
    ppo
    0.73
    inx
    0.71
    town
    0.70
    Act Density 0.031%

    No Known Activations