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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal obligations and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    statuses
    -0.15
    ëĭĿ
    -0.15
    ByteBuffer
    -0.15
     addCriterion
    -0.15
    etail
    -0.15
     returnUrl
    -0.14
    kenin
    -0.14
    ieg
    -0.14
    endif
    -0.14
    etti
    -0.14
    POSITIVE LOGITS
     deliberate
    0.23
     intentional
    0.21
     negligence
    0.19
     wil
    0.18
     reck
    0.18
     repeated
    0.17
     egreg
    0.17
     neglect
    0.17
     defiance
    0.16
    à¸Ĺร
    0.16
    Act Density 0.117%

    No Known Activations