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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that include the word "the" followed by quantifiers, indicators of comparisons, or the initiation of inquiries regarding specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cop
    -0.16
    ñ
    -0.14
    ord
    -0.14
     Quint
    -0.14
    lus
    -0.14
     cop
    -0.13
    aren
    -0.13
    beam
    -0.13
     (?,
    -0.13
     mantle
    -0.13
    POSITIVE LOGITS
    å±ĭ
    0.17
    686
    0.15
    ilden
    0.15
     difference
    0.15
    Composition
    0.14
    akah
    0.14
    ziel
    0.14
    elen
    0.14
    ORIZED
    0.14
    _readable
    0.13
    Act Density 0.027%

    No Known Activations