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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ij士
    -0.65
     advoc
    -0.57
    æ©
    -0.56
    swick
    -0.55
    efe
    -0.55
    gerald
    -0.55
    umbn
    -0.54
    ãĥ¯ãĥ³
    -0.54
    ãĥ¼ãĥĨãĤ£
    -0.53
     entreprene
    -0.53
    POSITIVE LOGITS
     Median
    0.75
     calories
    0.74
    ¶
    0.73
    )?
    0.72
     dstg
    0.69
     (%)
    0.69
     (~
    0.67
     median
    0.66
     depending
    0.64
     conson
    0.63
    Act Density 0.546%

    No Known Activations