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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between elements in data structures or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fletcher
    -0.82
     Mabel
    -0.79
     Mier
    -0.75
     Roper
    -0.74
     Cac
    -0.72
     Moro
    -0.67
     Fink
    -0.66
     Gabel
    -0.66
     Sable
    -0.64
     Frit
    -0.64
    POSITIVE LOGITS
     Kirkwood
    0.79
     Beauchamp
    0.79
     Jackman
    0.78
     Mayfield
    0.76
     Wiseman
    0.75
     Kenyatta
    0.74
     Heywood
    0.74
     Danilo
    0.74
     Jayne
    0.74
    verwijspagina
    0.73
    Act Density 1.374%

    No Known Activations