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

    Neuronpedia

    INDEX
    Explanations

    descriptions of criminal activities and police actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¥ŀ
    -0.92
    ãĤ§
    -0.91
    odox
    -0.90
    ahime
    -0.84
    anguage
    -0.78
    ãĤ¦ãĤ¹
    -0.76
    onom
    -0.76
    wcsstore
    -0.76
    isSpecialOrderable
    -0.76
    galitarian
    -0.75
    POSITIVE LOGITS
     suspected
    1.05
     sheriff
    1.03
     police
    1.01
     gunman
    0.99
     injured
    0.97
     unidentified
    0.93
     prosecutor
    0.91
     raided
    0.91
     hospital
    0.91
     emergency
    0.91
    Act Density 2.692%

    No Known Activations