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

    Neuronpedia

    INDEX
    Explanations

    code examples and explanations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ements
    -0.75
    alysed
    -0.70
    ima
    -0.66
    thal
    -0.64
    ogle
    -0.63
    resy
    -0.63
    incial
    -0.62
     inev
    -0.62
    ses
    -0.62
     Madness
    -0.62
    POSITIVE LOGITS
     suppose
    0.87
    tumblr
    0.83
     imagine
    0.78
     Suppose
    0.70
     hypot
    0.62
    inventory
    0.61
     consider
    0.60
    aeper
    0.59
     Proto
    0.58
     Logged
    0.58
    Act Density 0.149%

    No Known Activations