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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activities and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    of
    -0.16
    achen
    -0.16
    779
    -0.16
    ogan
    -0.15
    ITTE
    -0.15
    민
    -0.14
     Ru
    -0.14
    å¾Ģ
    -0.14
    inder
    -0.14
    ache
    -0.14
    POSITIVE LOGITS
     worden
    0.25
     werden
    0.20
     zosta
    0.19
    izzato
    0.18
    ÏĦαι
    0.17
     wurde
    0.17
     become
    0.17
     à¤Ĺय
    0.17
     becomes
    0.15
    sein
    0.15
    Act Density 0.007%

    No Known Activations