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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chn
    -0.16
     mass
    -0.16
     inter
    -0.15
    ews
    -0.15
    olumn
    -0.14
     fate
    -0.14
    ollar
    -0.14
     Gill
    -0.14
    ough
    -0.14
     Kho
    -0.14
    POSITIVE LOGITS
    istik
    0.17
    WithIdentifier
    0.15
     verdienen
    0.15
    åIJ
    0.15
    thood
    0.14
    uspend
    0.14
    pth
    0.14
    pras
    0.14
    pivot
    0.14
     Blick
    0.14
    Act Density 0.013%

    No Known Activations