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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey research results or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reform
    -0.16
    ilia
    -0.14
    ãĥ³ãĥij
    -0.14
    kil
    -0.14
     gv
    -0.14
    endale
    -0.14
    ucher
    -0.13
    uida
    -0.13
    İ
    -0.13
    worth
    -0.13
    POSITIVE LOGITS
    âĶĺ
    0.16
     Eisen
    0.14
    uras
    0.14
    edly
    0.14
    med
    0.14
    /results
    0.14
     kvinde
    0.13
    Äįel
    0.13
     norske
    0.13
    磨
    0.13
    Act Density 0.032%

    No Known Activations