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

    Neuronpedia

    INDEX
    Explanations

    addresses or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific addresses and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     probes
    -0.76
     seals
    -0.73
     whisk
    -0.71
     herds
    -0.70
     flavours
    -0.70
     sources
    -0.69
     transcripts
    -0.69
     awa
    -0.68
     braces
    -0.68
     spreads
    -0.67
    POSITIVE LOGITS
     Hyde
    0.84
     Avalon
    0.84
     KL
    0.82
     Lexington
    0.76
     Indianapolis
    0.76
     Providence
    0.75
     Blvd
    0.75
     Kuala
    0.75
     Jacksonville
    0.75
    arcity
    0.73
    Act Density 0.335%

    No Known Activations