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

    Neuronpedia

    INDEX
    Explanations

    references to academic work and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adero
    -0.17
    hetto
    -0.15
    deniz
    -0.15
    translated
    -0.15
     Leisure
    -0.15
    KeyCode
    -0.14
    istung
    -0.14
    UTILITY
    -0.14
    WEEN
    -0.14
    umhur
    -0.14
    POSITIVE LOGITS
     corpor
    0.25
     Corpus
    0.22
     Corpor
    0.21
     corpus
    0.21
     Phon
    0.20
     Morph
    0.20
    morph
    0.19
     prag
    0.19
     Language
    0.19
     Lingu
    0.19
    Act Density 0.024%

    No Known Activations