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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating change or transformation in appearance and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ook
    -0.15
    at
    -0.14
    aba
    -0.13
    331
    -0.13
     cho
    -0.13
    ey
    -0.13
     phenomena
    -0.13
     Sheldon
    -0.13
    rex
    -0.13
     choice
    -0.13
    POSITIVE LOGITS
     meaning
    0.26
     significance
    0.24
     meanings
    0.23
     shape
    0.21
    meaning
    0.20
     Meaning
    0.20
     importance
    0.20
     status
    0.20
     dimensions
    0.19
     characteristics
    0.19
    Act Density 0.275%

    No Known Activations