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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, particularly the first names "Tucker," "Kle," and "Clare."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lantern
    -0.81
     ring
    -0.81
     mir
    -0.81
    LOD
    -0.79
     cal
    -0.74
     bin
    -0.72
    MAP
    -0.71
    Wind
    -0.70
    Abyss
    -0.69
     batter
    -0.68
    POSITIVE LOGITS
     Tucker
    3.20
    ucker
    2.47
     Kle
    1.63
     Milo
    1.36
     Clare
    1.31
     Buckley
    1.24
     Bezos
    1.14
     Lemon
    1.10
     Veronica
    1.04
     Coulter
    1.04
    Act Density 0.045%

    No Known Activations