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

    Neuronpedia

    INDEX
    Explanations

    names of cities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pod
    -0.80
    pec
    -0.75
     ar
    -0.73
     Announce
    -0.71
     brace
    -0.71
    Arab
    -0.70
     pal
    -0.70
     Pod
    -0.68
     declare
    -0.68
    pod
    -0.68
    POSITIVE LOGITS
     Everett
    2.86
     Leone
    1.87
     Sutton
    1.85
     Foster
    1.80
     Slater
    1.73
    verett
    1.60
     Cullen
    1.47
     McCabe
    1.40
     Buckley
    1.36
     Kirby
    1.35
    Act Density 0.031%

    No Known Activations