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

    Neuronpedia

    INDEX
    Explanations

    the name "Smith."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Cale
    -0.80
     TTC
    -0.79
     Dile
    -0.78
     cale
    -0.76
     Arka
    -0.75
     Dica
    -0.75
    Dile
    -0.74
    chere
    -0.73
     ‚
    -0.73
     Haga
    -0.73
    POSITIVE LOGITS
     Smith
    1.65
     SMITH
    1.52
    SMITH
    1.52
     smith
    1.48
    Smith
    1.44
    smith
    1.41
     Smiths
    1.39
    mith
    1.20
     Smit
    1.16
    Smit
    1.04
    Act Density 0.008%

    No Known Activations