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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions or coding concepts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ministic
    -0.84
    heid
    -0.79
    earances
    -0.73
    ivo
    -0.72
    agents
    -0.72
    oral
    -0.70
    inian
    -0.70
    anny
    -0.69
    acion
    -0.69
    rophe
    -0.69
    POSITIVE LOGITS
     up
    1.28
     out
    1.02
    Up
    0.99
    up
    0.95
    GGGGGGGG
    0.94
    ups
    0.89
     Up
    0.89
    GGGG
    0.88
    UP
    0.87
     down
    0.85
    Act Density 3.631%

    No Known Activations