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

    Neuronpedia

    INDEX
    Explanations

    names or proper nouns with a specific letter pattern

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the letter 'h'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.72
     Clause
    -0.70
    é¾įå¥ij士
    -0.61
     Kush
    -0.61
     Weeks
    -0.59
     Everywhere
    -0.59
    terday
    -0.57
     heartbeat
    -0.57
     Bigfoot
    -0.57
     First
    -0.56
    POSITIVE LOGITS
    Ãī
    0.91
    vor
    0.88
    oys
    0.86
    aus
    0.83
    acia
    0.82
    arten
    0.79
    alt
    0.78
    och
    0.78
    uit
    0.76
    ttp
    0.76
    Act Density 0.031%

    No Known Activations