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

    Neuronpedia

    INDEX
    Explanations

    terms related to racism and associated negative behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azen
    -0.15
    913
    -0.15
    erialized
    -0.14
    ãĥ£
    -0.14
    obo
    -0.14
    eron
    -0.14
    enn
    -0.14
    akov
    -0.14
    oby
    -0.14
    ogue
    -0.14
    POSITIVE LOGITS
    FormatException
    0.15
    yr
    0.15
    dde
    0.15
    wake
    0.14
     depos
    0.14
    oldt
    0.14
    isos
    0.13
    elsey
    0.13
    ettle
    0.13
    inals
    0.13
    Act Density 0.018%

    No Known Activations