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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.80
     Confederation
    -0.80
    culosis
    -0.79
    ashtra
    -0.69
    âĶĢâĶĢ
    -0.69
     Dhabi
    -0.67
    terday
    -0.67
    renheit
    -0.66
    >>\
    -0.65
    duino
    -0.65
    POSITIVE LOGITS
    isner
    0.83
    oner
    0.83
    aney
    0.82
    antz
    0.81
    utsch
    0.80
    agan
    0.78
    agg
    0.78
    onson
    0.78
    iggs
    0.74
    iso
    0.74
    Act Density 0.198%

    No Known Activations