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

    Neuronpedia

    INDEX
    Explanations

    names of people or places in a news article

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' names or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.87
    krit
    -0.79
    ower
    -0.78
    legged
    -0.77
    ply
    -0.77
    pick
    -0.71
    taker
    -0.71
    ngth
    -0.70
    cipled
    -0.70
    sonian
    -0.70
    POSITIVE LOGITS
     Nieto
    1.33
     Gomez
    1.31
     Torres
    1.27
     Ramos
    1.27
     Chavez
    1.27
     Gonzalez
    1.24
     Diaz
    1.23
     Flores
    1.21
     Rivera
    1.19
     Enrique
    1.18
    Act Density 0.368%

    No Known Activations