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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and action-related terms in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.16
     seins
    -0.16
    Spl
    -0.15
    lix
    -0.14
     paramMap
    -0.14
    ranÃŃ
    -0.14
     apt
    -0.13
    trash
    -0.13
    λ
    -0.13
     доб
    -0.13
    POSITIVE LOGITS
    itespace
    0.15
    Å¡ÃŃ
    0.15
    icode
    0.14
    eczy
    0.14
    noop
    0.14
    .accel
    0.14
    incare
    0.14
     Roberts
    0.14
    avic
    0.14
    UGE
    0.14
    Act Density 0.035%

    No Known Activations