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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" or variations of the verb "to be."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nakalista
    -1.16
    UnusedPrivate
    -1.02
     $_"
    -1.02
     myſelf
    -1.02
     autorytatywna
    -0.98
    ]")
    -0.97
     lenker
    -0.94
     ſeveral
    -0.94
    :].
    -0.94
    таратура
    -0.91
    POSITIVE LOGITS
    m
    0.83
    tom
    0.69
    um
    0.65
    mh
    0.63
    mi
    0.63
    Bom
    0.63
    Im
    0.63
     am
    0.62
    im
    0.61
    t
    0.61
    Act Density 0.038%

    No Known Activations