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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "not so"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.62
    ertodd
    -0.60
     overflow
    -0.60
     (>
    -0.59
    MAP
    -0.58
     expire
    -0.57
    viron
    -0.56
    neum
    -0.56
     Eth
    -0.55
    DERR
    -0.54
    POSITIVE LOGITS
     much
    1.15
    much
    0.87
    bered
    0.85
    vier
    0.83
     forgiving
    0.83
     lucky
    0.83
     fortunate
    0.81
     easy
    0.79
     simple
    0.75
     subtly
    0.75
    Act Density 0.033%

    No Known Activations