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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles preceded by the word "on"

    oai_token-act-pair · gpt-3.5-turbo

    references to Twitter handles and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )",
    -0.78
     ?)
    -0.69
    ?",
    -0.67
    "))
    -0.66
     cumbers
    -0.66
    )=
    -0.65
     standby
    -0.64
     mileage
    -0.63
     Ended
    -0.63
     accelerated
    -0.62
    POSITIVE LOGITS
    odcast
    0.98
    <|endoftext|>
    0.96
    _.
    0.95
    Brow
    0.91
    biz
    0.89
    Jr
    0.84
    apps
    0.84
    pod
    0.82
    Stud
    0.82
    football
    0.82
    Act Density 0.071%

    No Known Activations