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

    Neuronpedia

    INDEX
    Explanations

    instances of a specific Italian phrase

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lla."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.92
     citiz
    -0.83
    States
    -0.80
    states
    -0.73
     unden
    -0.71
    livious
    -0.68
    ß
    -0.67
    lay
    -0.66
    LESS
    -0.66
    Þ
    -0.66
    POSITIVE LOGITS
    ppo
    1.09
    lla
    1.07
    uthor
    0.97
    ppa
    0.97
    zzo
    0.96
    ppe
    0.95
    ignt
    0.82
    ñ
    0.82
    quist
    0.82
     Rosa
    0.80
    Act Density 0.011%

    No Known Activations