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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strict rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zend
    -0.17
    ock
    -0.16
     kadar
    -0.15
    aż
    -0.15
    ekim
    -0.14
    onia
    -0.14
    OffsetTable
    -0.13
    å¨ĺ
    -0.13
    onen
    -0.13
    /linux
    -0.13
    POSITIVE LOGITS
    /fast
    0.17
    ness
    0.16
    y
    0.16
    ely
    0.16
    tics
    0.15
    est
    0.14
    imedia
    0.14
     Wand
    0.14
    210
    0.14
    -c
    0.14
    Act Density 0.025%

    No Known Activations