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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sunder
    -0.14
     dip
    -0.14
    Çİ
    -0.13
    frey
    -0.13
    æĥ³
    -0.13
    iap
    -0.13
    ollar
    -0.13
    Comfort
    -0.13
    Ãłi
    -0.13
    Merit
    -0.13
    POSITIVE LOGITS
    querque
    0.18
    antly
    0.18
    abby
    0.16
    iez
    0.16
    á»ĵi
    0.15
     gang
    0.15
    utsche
    0.15
    aben
    0.15
    afia
    0.15
    صر
    0.15
    Act Density 0.053%

    No Known Activations