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

    Neuronpedia

    INDEX
    Explanations

    details related to academic studies and research projects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     immobil
    -0.42
     dispers
    -0.40
     manif
    -0.38
     spokes
    -0.38
     behavi
    -0.38
     stewards
    -0.38
     destro
    -0.38
     casting
    -0.38
     Afric
    -0.37
     fert
    -0.37
    POSITIVE LOGITS
    redits
    0.51
    ================================================================
    0.50
    Reviewed
    0.47
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.47
    Avg
    0.46
    ĸļ
    0.45
    region
    0.45
    ournals
    0.44
    wcsstore
    0.44
    aples
    0.43
    Act Density 5.639%

    No Known Activations