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

    Neuronpedia

    INDEX
    Explanations

    the string "mi" with an activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mi" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.92
    swick
    -0.89
    egg
    -0.83
    rooms
    -0.82
    tions
    -0.81
    IBLE
    -0.77
    glers
    -0.76
    fully
    -0.73
    lift
    -0.72
    space
    -0.71
    POSITIVE LOGITS
    ya
    0.91
    wi
    0.87
    oti
    0.87
    ño
    0.80
    otti
    0.80
    ovember
    0.80
    wana
    0.78
    omi
    0.75
    ña
    0.74
    opsis
    0.74
    Act Density 0.010%

    No Known Activations