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

    Neuronpedia

    INDEX
    Explanations

    city or location names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of locations and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.83
     meanwhile
    -0.81
     BBC
    -0.77
     Icelandic
    -0.75
     MEP
    -0.74
     Gujar
    -0.71
     apologise
    -0.71
     Subtle
    -0.70
     Indones
    -0.69
     silenced
    -0.69
    POSITIVE LOGITS
    esville
    1.54
    erville
    1.48
    endale
    1.41
    mington
    1.38
    heny
    1.33
    eston
    1.26
    lington
    1.23
    auga
    1.21
    adelphia
    1.19
    onia
    1.17
    Act Density 0.204%

    No Known Activations