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

    Neuronpedia

    INDEX
    Explanations

    people's names, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shorth
    -0.64
     corrid
    -0.58
    veh
    -0.58
     subscript
    -0.57
    Spanish
    -0.57
    Prim
    -0.57
     smugglers
    -0.56
     suffix
    -0.56
    Assembly
    -0.54
    Girls
    -0.54
    POSITIVE LOGITS
     Jr
    1.12
    zyk
    0.95
    enegger
    0.91
    opoulos
    0.91
    sson
    0.86
     Sr
    0.84
     III
    0.84
    oulos
    0.82
    oglu
    0.81
    ewski
    0.80
    Act Density 0.373%

    No Known Activations