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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the name "David."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    paravant
    -0.74
     whoſe
    -0.68
    ctus
    -0.68
    ’?
    -0.66
    /#/
    -0.66
     Monfieur
    -0.66
    sno
    -0.65
    corrhi
    -0.64
     slu
    -0.63
    ?”,
    -0.63
    POSITIVE LOGITS
     David
    1.30
    David
    1.25
    DAVID
    1.20
     Davids
    1.12
     DAVID
    1.09
     david
    1.07
    david
    1.02
     Davido
    0.91
     Meksiku
    0.90
     Goliath
    0.89
    Act Density 0.007%

    No Known Activations