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

    Neuronpedia

    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tokens
    -0.75
    Ô
    -0.74
    ividual
    -0.73
     vortex
    -0.73
     womb
    -0.72
    Spoiler
    -0.70
     geop
    -0.64
     offline
    -0.62
     arrang
    -0.61
     tablets
    -0.60
    POSITIVE LOGITS
    iana
    0.83
     Chapman
    0.80
     Lamb
    0.80
     Burns
    0.80
     Bent
    0.78
     Breed
    0.78
     Canaver
    0.76
     Br
    0.75
    angelo
    0.74
     Mend
    0.74
    Act Density 0.155%

    No Known Activations