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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "He" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĦ
    -0.66
     Esk
    -0.64
    ignt
    -0.62
    س
    -0.62
    代
    -0.61
    Temperature
    -0.58
     sum
    -0.58
    éĢ
    -0.58
    ãĤ§
    -0.57
     1913
    -0.55
    POSITIVE LOGITS
    resy
    1.15
    zbollah
    1.08
    'll
    0.97
    pherd
    0.90
    'd
    0.88
    gemony
    0.87
    reditary
    0.87
    ppard
    0.86
     encount
    0.84
    avier
    0.83
    Act Density 0.085%

    No Known Activations