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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and technical documentation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     affili
    -0.80
     waged
    -0.75
     escort
    -0.73
     commemor
    -0.72
     apparel
    -0.70
     patron
    -0.70
     mourn
    -0.70
     touring
    -0.70
     funer
    -0.69
     idol
    -0.69
    POSITIVE LOGITS
     Suppose
    1.24
    txt
    1.23
    example
    1.22
    lua
    1.21
     Basically
    1.21
     Example
    1.21
     Therefore
    1.20
    Usage
    1.20
     Alternatively
    1.20
     Using
    1.19
    Act Density 0.234%

    No Known Activations