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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hennessy
    -0.76
    ExtendWith
    -0.73
     Magdalen
    -0.72
     Bowen
    -0.69
     Rodin
    -0.67
     Landis
    -0.66
     Burma
    -0.66
     Krakow
    -0.66
     Lorena
    -0.65
     Jacinto
    -0.64
    POSITIVE LOGITS
     Klee
    0.89
     Garr
    0.78
     Colbert
    0.74
     Ebert
    0.73
     Papi
    0.73
     Caldwell
    0.72
     Frie
    0.72
     Pene
    0.71
     Sando
    0.70
     Arora
    0.70
    Act Density 1.665%

    No Known Activations