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

    Neuronpedia

    INDEX
    Explanations

    instances and potential consequences related to accidents and safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    accidents and injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StringCopy
    -0.40
     Wicidata
    -0.39
     continúas
    -0.38
    UnknownFields
    -0.37
    CppMethod
    -0.36
    󠁴
    -0.35
    endcsname
    -0.35
    pushFollow
    -0.35
    LINKS
    -0.33
    ançon
    -0.33
    POSITIVE LOGITS
     tragedia
    0.52
     tragé
    0.52
     fatal
    0.50
     Verlet
    0.49
     accidents
    0.49
    Hentet
    0.48
     malheure
    0.48
     دیکھیے
    0.48
     injuries
    0.47
     vícti
    0.47
    Act Density 0.021%

    No Known Activations