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

    Neuronpedia

    INDEX
    Explanations

    words related to surveillance and monitoring

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.79
    */(
    -0.70
    anchester
    -0.66
     Sachs
    -0.61
     Unch
    -0.60
    oulder
    -0.59
    rongh
    -0.57
     Kinnikuman
    -0.56
    )].
    -0.56
     coord
    -0.55
    POSITIVE LOGITS
    illance
    0.83
    schild
    0.81
    cliffe
    0.78
     Annotations
    0.78
    xual
    0.71
    istan
    0.66
    chal
    0.65
    åĤ
    0.64
    roid
    0.64
     COURT
    0.63
    Act Density 0.078%

    No Known Activations