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

    Neuronpedia

    INDEX
    Explanations

    names of specific locations or towns

    oai_token-act-pair · gpt-3.5-turbo

    specific names of places and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.84
     censored
    -0.70
     subscript
    -0.69
    erity
    -0.69
     assistants
    -0.68
     guy
    -0.68
     censor
    -0.67
     biography
    -0.66
    =-=-=-=-
    -0.65
     odds
    -0.65
    POSITIVE LOGITS
     Island
    1.04
    opolis
    1.04
     Junction
    1.03
     Resort
    0.99
     Valley
    0.96
     Village
    0.96
     Township
    0.95
     Town
    0.95
     Peninsula
    0.93
     District
    0.91
    Act Density 0.419%

    No Known Activations