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

    Neuronpedia

    INDEX
    Explanations

    references to murals and graffiti

    oai_token-act-pair · gpt-3.5-turbo

    references to murals and public art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferr
    -0.79
     Templar
    -0.77
     Stra
    -0.75
    ENDED
    -0.75
     Bond
    -0.70
    OTAL
    -0.69
     Samurai
    -0.68
     Crusher
    -0.68
     Primal
    -0.67
     Schwarzenegger
    -0.67
    POSITIVE LOGITS
     mur
    1.11
     mural
    1.06
    vine
    0.84
     paintings
    0.83
     indu
    0.80
    mur
    0.78
     leve
    0.77
     painting
    0.75
     art
    0.74
     artwork
    0.72
    Act Density 0.018%

    No Known Activations