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

    Neuronpedia

    INDEX
    Explanations

    words related to information technology, software development, and programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lets
    -0.61
    hots
    -0.61
    stru
    -0.59
    ãĤ£
    -0.58
    wards
    -0.58
    itive
    -0.58
    ãĥ£
    -0.58
     biod
    -0.57
    ignty
    -0.56
    ãĥ©ãĥ³
    -0.56
    POSITIVE LOGITS
    ICLE
    0.95
    IONS
    0.94
    LAND
    0.94
    TY
    0.92
    UTE
    0.90
    TING
    0.89
    UAL
    0.88
    ABLE
    0.88
    LESS
    0.87
    MIN
    0.86
    Act Density 3.542%

    No Known Activations