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

    Neuronpedia

    INDEX
    Explanations

    keywords related to criminal activity or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.81
    swer
    -0.73
    apons
    -0.69
     cabinets
    -0.67
     hect
    -0.66
     namely
    -0.66
    cation
    -0.65
    itate
    -0.63
    tion
    -0.63
     sq
    -0.62
    POSITIVE LOGITS
    NPR
    0.83
    Jere
    0.76
    Copyright
    0.74
    Brian
    0.73
    Thom
    0.72
    Owner
    0.71
    Latest
    0.71
    Todd
    0.70
    Larry
    0.70
    CNN
    0.70
    Act Density 0.008%

    No Known Activations