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

    Neuronpedia

    INDEX
    Explanations

    titles of TV shows and movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.76
     tremend
    -0.76
    ivable
    -0.69
    uggest
    -0.69
    etooth
    -0.68
     trouble
    -0.67
    bered
    -0.66
    avorite
    -0.65
    agonal
    -0.63
    azo
    -0.63
    POSITIVE LOGITS
     Provided
    0.95
     Become
    0.85
     https
    0.83
     Prelude
    0.78
    YES
    0.78
     http
    0.76
    hover
    0.76
     TBD
    0.75
     Rise
    0.74
     Volume
    0.74
    Act Density 0.337%

    No Known Activations