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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and references to objects in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ds
    -0.17
    in
    -0.17
    alo
    -0.16
    re
    -0.15
    be
    -0.15
     penn
    -0.15
    523
    -0.14
     Knife
    -0.14
     hala
    -0.14
    if
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.21
     OMIT
    0.18
    _mC
    0.16
    ozem
    0.15
    λή
    0.15
    à¤ľà¤¨
    0.15
    chwitz
    0.15
    'gc
    0.15
    CallCheck
    0.15
    fte
    0.15
    Act Density 0.048%

    No Known Activations