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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical details and explanations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.83
    foreseen
    -0.77
    DragonMagazine
    -0.77
    ocene
    -0.71
    andom
    -0.70
    ersive
    -0.70
    vernment
    -0.69
    mone
    -0.68
    mercial
    -0.67
    utenberg
    -0.66
    POSITIVE LOGITS
    ndra
    0.94
     enough
    0.87
    entimes
    0.82
    fire
    0.82
     tack
    0.75
    lly
    0.75
    ty
    0.74
    ness
    0.72
    ties
    0.72
    coat
    0.70
    Act Density 6.758%

    No Known Activations