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

    Neuronpedia

    INDEX
    Explanations

    instances of the first-person pronoun "I" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Probably
    -0.91
    probably
    -0.88
     probably
    -0.87
    Probably
    -0.84
     probabilmente
    -0.72
     provavelmente
    -0.69
    enumi
    -0.65
     wahrscheinlich
    -0.65
     probablemente
    -0.64
     presumably
    -0.63
    POSITIVE LOGITS
     were
    1.56
    Were
    1.32
     weren
    1.29
     Were
    1.25
     WERE
    1.19
     ever
    1.19
    were
    1.18
     hadn
    1.00
    weren
    0.98
     EVER
    0.86
    Act Density 0.261%

    No Known Activations