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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles with varying numbers in them

    oai_token-act-pair · gpt-3.5-turbo

    user mentions or social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shrink
    -0.72
     breadth
    -0.66
     captcha
    -0.65
     shortage
    -0.62
    NetMessage
    -0.60
     swelling
    -0.60
     Gree
    -0.59
     Barrier
    -0.59
     pressure
    -0.59
    Bound
    -0.59
    POSITIVE LOGITS
    /)
    0.94
    Jr
    0.83
    )
    0.83
    reports
    0.82
    CTV
    0.82
    yssey
    0.80
    enegger
    0.78
    afort
    0.78
    hester
    0.77
    /.
    0.77
    Act Density 0.077%

    No Known Activations