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

    Neuronpedia

    INDEX
    Explanations

    references to publishing or sharing information and specific publication-related details like dates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    utic
    -0.80
    adra
    -0.76
    porary
    -0.75
    antics
    -0.72
    ixel
    -0.71
    adr
    -0.70
    vette
    -0.69
    mini
    -0.68
    otropic
    -0.68
    xus
    -0.65
    POSITIVE LOGITS
     aloud
    0.79
     Date
    0.73
    Published
    0.69
     Published
    0.68
     Prediction
    0.68
     Decision
    0.64
     Apr
    0.64
    NESS
    0.64
     Stories
    0.63
    âĸ¬
    0.60
    Act Density 7.459%

    No Known Activations