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

    Neuronpedia

    INDEX
    Explanations

    elements that quantify or specify conditions, requirements, or attributes in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyn
    -0.15
    hir
    -0.15
     Crack
    -0.14
     tur
    -0.14
     Daw
    -0.14
    ures
    -0.14
    Å¡ti
    -0.14
    hesive
    -0.14
    anner
    -0.13
    entials
    -0.13
    POSITIVE LOGITS
    íĽĦ
    0.17
     degree
    0.15
    degree
    0.14
    kening
    0.14
    inker
    0.14
     stage
    0.14
    ëĬIJ
    0.14
     zá
    0.14
    endez
    0.14
    atives
    0.14
    Act Density 0.077%

    No Known Activations