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

    Neuronpedia

    INDEX
    Explanations

    references to itemized lists or agendas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atte
    -0.15
    bart
    -0.14
    eln
    -0.14
     errs
    -0.14
     McCabe
    -0.14
    ÑĬ
    -0.14
    891
    -0.14
    484
    -0.14
     Instructor
    -0.14
    _helpers
    -0.13
    POSITIVE LOGITS
    unga
    0.19
     deleg
    0.18
    UNCT
    0.18
     prepar
    0.17
    -session
    0.17
     Rap
    0.17
     session
    0.17
     Oyun
    0.16
     pl
    0.16
    목
    0.16
    Act Density 0.040%

    No Known Activations