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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adler
    -0.17
    olon
    -0.17
    ullo
    -0.15
     Bingo
    -0.15
    icher
    -0.15
     Grove
    -0.14
    opoulos
    -0.14
    atty
    -0.14
    ettle
    -0.14
    -cur
    -0.14
    POSITIVE LOGITS
     Knot
    0.16
    enet
    0.15
    pu
    0.15
    /msg
    0.15
    ener
    0.15
    abe
    0.14
    agen
    0.14
    met
    0.14
    728
    0.14
    ortal
    0.14
    Act Density 0.024%

    No Known Activations