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

    Neuronpedia

    INDEX
    Explanations

    critiques or evaluates behaviors or traits

    oai_token-act-pair · gpt-3.5-turbo

    references to specific films or artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewitness
    -0.89
    Detailed
    -0.77
    Government
    -0.75
    Emergency
    -0.74
    Increase
    -0.73
     POS
    -0.72
    ICO
    -0.72
    `.
    -0.71
     emergency
    -0.69
    panic
    -0.69
    POSITIVE LOGITS
     Whedon
    1.22
     Songs
    1.00
     Kubrick
    0.96
     composer
    0.96
     premiered
    0.90
     Cannes
    0.90
     homage
    0.88
     Spielberg
    0.87
     Lovecraft
    0.86
     Gaga
    0.85
    Act Density 0.782%

    No Known Activations