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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lished
    -0.81
     Editorial
    -0.76
    abase
    -0.71
     transitions
    -0.69
     margins
    -0.69
     constituencies
    -0.69
     synerg
    -0.68
    pmwiki
    -0.68
     Quarterly
    -0.67
     debates
    -0.67
    POSITIVE LOGITS
     raping
    0.91
     daddy
    0.88
     Allah
    0.87
     tresp
    0.87
     robbery
    0.86
     intruder
    0.85
     ransom
    0.82
     burgl
    0.82
     kidnapping
    0.81
     cocaine
    0.80
    Act Density 0.385%

    No Known Activations