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

    Neuronpedia

    INDEX
    Explanations

    punctuations and variations of the word "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stanton
    -0.14
    chio
    -0.14
     shake
    -0.14
    anten
    -0.14
    ascript
    -0.14
    Checks
    -0.13
    ENO
    -0.13
    ithe
    -0.13
    ths
    -0.13
     Cass
    -0.13
    POSITIVE LOGITS
     Glover
    0.17
    γε
    0.16
     Brand
    0.14
     López
    0.14
    arest
    0.14
    ñana
    0.14
    Brand
    0.14
    lsen
    0.14
    ár
    0.14
    _barrier
    0.14
    Act Density 0.001%

    No Known Activations