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

    Neuronpedia

    INDEX
    Explanations

    references to null values and boolean states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \grid
    -0.16
    .gwt
    -0.16
     Haram
    -0.15
     )↵↵↵↵↵↵↵↵
    -0.15
    ofday
    -0.14
     TestUtils
    -0.13
    caret
    -0.13
    ODY
    -0.13
    ÛĮÙĩ
    -0.13
    ritis
    -0.13
    POSITIVE LOGITS
    ;↵
    0.16
    istant
    0.15
    ÑĢажд
    0.15
    ucher
    0.14
     Keller
    0.14
    j
    0.14
    ilter
    0.14
    ιλο
    0.14
    ints
    0.14
    ;↵↵
    0.14
    Act Density 0.067%

    No Known Activations