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

    Neuronpedia

    INDEX
    Explanations

    software or programming-related content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rian
    -0.35
    erenn
    -0.34
     Barbarian
    -0.33
     reviewer
    -0.31
    ourgeois
    -0.30
    erion
    -0.30
     hairst
    -0.30
     glam
    -0.30
    geist
    -0.29
    alli
    -0.29
    POSITIVE LOGITS
    ################
    0.36
    ...]
    0.35
     ..........
    0.33
    othal
    0.33
    addon
    0.32
    uania
    0.32
     ......
    0.31
    :,
    0.31
    ###
    0.31
     Wink
    0.30
    Act Density 0.187%

    No Known Activations