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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantitative measurements, such as percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and statistical metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corro
    -0.56
    Äĩ
    -0.52
    natureconservancy
    -0.50
     rhet
    -0.48
     deterior
    -0.47
     accent
    -0.45
    anian
    -0.45
     crim
    -0.44
     contaminated
    -0.44
    imity
    -0.44
    POSITIVE LOGITS
    ·
    0.74
    ī
    0.72
    ®
    0.68
    »
    0.67
    «
    0.66
    IJ
    0.63
    OHN
    0.63
    º
    0.62
    ĵĺ
    0.62
    ãĥ¼ãĥĨãĤ£
    0.61
    Act Density 2.350%

    No Known Activations