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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏįÏĦε
    -0.14
    ãĥªãĤ¢
    -0.14
     Barr
    -0.14
    avis
    -0.13
    Persistence
    -0.13
     OTHERWISE
    -0.13
    zel
    -0.13
    her
    -0.13
    ehr
    -0.13
     Tas
    -0.13
    POSITIVE LOGITS
    essel
    0.15
     Hi
    0.15
    idget
    0.15
    ekler
    0.14
    _HI
    0.14
    createFrom
    0.14
    ÑĢед
    0.14
    hi
    0.14
    Hi
    0.14
    Ĵáŀ
    0.13
    Act Density 0.039%

    No Known Activations