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

    Neuronpedia

    INDEX
    Explanations

    mention of the name "Tom."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Calla
    -0.83
    Griffin
    -0.77
     Griffin
    -0.74
     Spro
    -0.72
    ěstí
    -0.69
     Rena
    -0.69
    ulemon
    -0.69
    igshid
    -0.68
    PMA
    -0.68
    recip
    -0.67
    POSITIVE LOGITS
    Tom
    1.40
     Tom
    1.33
     Toms
    1.27
     Tomcat
    1.19
     tomatoes
    1.18
     Tomatoes
    1.18
     Tomlinson
    1.16
     Tompkins
    1.11
     TOM
    1.09
     Tomar
    1.06
    Act Density 0.007%

    No Known Activations