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

    Neuronpedia

    INDEX
    Explanations

    negative commands or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anker
    -0.15
    versation
    -0.14
    оÑĢе
    -0.14
    lette
    -0.13
    ghan
    -0.13
     STDERR
    -0.13
    557
    -0.13
    iling
    -0.13
    anki
    -0.13
     corruption
    -0.13
    POSITIVE LOGITS
    olver
    0.17
    DT
    0.16
     unless
    0.16
     yourself
    0.15
     Unless
    0.15
    rush
    0.15
    Unless
    0.15
     laten
    0.14
     absol
    0.14
     too
    0.14
    Act Density 0.094%

    No Known Activations