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

    Neuronpedia

    INDEX
    Explanations

    terms related to penalties and punitive measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.17
    arent
    -0.16
    PPP
    -0.15
    illon
    -0.14
    /windows
    -0.14
    /material
    -0.14
    ellers
    -0.14
    eyim
    -0.14
    kul
    -0.13
    ismus
    -0.13
    POSITIVE LOGITS
     met
    0.22
     lev
    0.21
    ishment
    0.19
     handed
    0.17
     severity
    0.16
     severe
    0.16
    quet
    0.16
     reserved
    0.16
    met
    0.15
     Lev
    0.15
    Act Density 0.059%

    No Known Activations