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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions and events involving people and objects

    oai_token-act-pair · gpt-3.5-turbo

    instances of surveillance or video footage involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @#&
    -0.78
    ãĤ¦ãĤ¹
    -0.73
    needed
    -0.72
     Ratings
    -0.71
    politics
    -0.67
    Prem
    -0.65
    idays
    -0.65
    lished
    -0.64
    Sov
    -0.64
    minimum
    -0.63
    POSITIVE LOGITS
     kneeling
    1.09
     flanked
    1.01
     caption
    0.98
     silhouette
    0.97
     silhou
    0.96
     grinning
    0.95
     smiling
    0.95
     handcuffed
    0.95
     menacing
    0.93
     POV
    0.87
    Act Density 0.534%

    No Known Activations