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

    Neuronpedia

    INDEX
    Explanations

    references to film and television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eft
    -0.17
    longleftrightarrow
    -0.16
     Darth
    -0.15
    948
    -0.15
    uncated
    -0.14
    å¸Ń
    -0.14
    åıĶ
    -0.14
    .Network
    -0.14
    bidden
    -0.13
    PackageManager
    -0.13
    POSITIVE LOGITS
     Sahara
    0.18
     Maid
    0.16
    yz
    0.16
    alte
    0.16
     Extract
    0.15
     Hancock
    0.15
     Evan
    0.15
     adaptation
    0.15
    BASE
    0.15
    XXX
    0.15
    Act Density 0.029%

    No Known Activations