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

    Neuronpedia

    INDEX
    Explanations

    references to murder and conspiracy-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Offensive
    -0.16
    anke
    -0.16
     Thief
    -0.15
    à¸Ĺาà¸Ļ
    -0.14
     %-
    -0.14
     Disaster
    -0.14
     confiscated
    -0.14
    ertino
    -0.13
    üz
    -0.13
     Cata
    -0.13
    POSITIVE LOGITS
     killing
    0.59
     kill
    0.56
    kill
    0.53
     murder
    0.52
     kills
    0.50
     killings
    0.50
     killed
    0.49
    mur
    0.48
     Kill
    0.47
    Kill
    0.47
    Act Density 0.412%

    No Known Activations