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

    Neuronpedia

    INDEX
    Explanations

    references to instructions, implementation difficulties, and discussions around casual online interactions or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrNil
    -0.15
    letion
    -0.14
     NotSupportedException
    -0.14
     closed
    -0.14
    leta
    -0.14
     Sanchez
    -0.14
    ãĤ«ãĥĨãĤ´ãĥª
    -0.14
    ká
    -0.14
    lein
    -0.14
    rete
    -0.14
    POSITIVE LOGITS
     Cul
    0.16
    POCH
    0.15
    λιο
    0.15
    IBC
    0.14
    206
    0.14
     Karn
    0.14
    клад
    0.14
    访
    0.14
     imm
    0.13
    oes
    0.13
    Act Density 0.009%

    No Known Activations