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

    Neuronpedia

    INDEX
    Explanations

    information about various news sources and websites

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that indicate the source of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cradle
    -0.83
     sway
    -0.82
     butcher
    -0.77
     portrait
    -0.77
     dispers
    -0.77
     electr
    -0.76
     involuntary
    -0.76
     unstoppable
    -0.75
     stocking
    -0.74
     hitch
    -0.74
    POSITIVE LOGITS
    com
    1.33
    Org
    1.15
    org
    1.13
    fm
    1.12
    net
    1.09
    gov
    1.07
    edu
    1.05
    dll
    1.00
    tv
    1.00
    exe
    0.99
    Act Density 0.522%

    No Known Activations