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

    Neuronpedia

    INDEX
    Explanations

    TV show titles

    oai_token-act-pair · gpt-3.5-turbo

    references to television shows or media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.70
     proble
    -0.70
     tomat
    -0.69
     Observatory
    -0.64
     condem
    -0.64
    enegger
    -0.63
    ivated
    -0.63
     tension
    -0.62
    ktop
    -0.62
     oun
    -0.61
    POSITIVE LOGITS
    cffffcc
    0.85
    lean
    0.83
    ï¸ı
    0.82
    âĵĺ
    0.80
    ever
    0.80
    âĶĢâĶĢ
    0.79
    null
    0.78
    conom
    0.78
    else
    0.78
    âĶĢâĶĢâĶĢâĶĢ
    0.77
    Act Density 0.136%

    No Known Activations