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

    Neuronpedia

    INDEX
    Explanations

    titles of books

    oai_token-act-pair · gpt-3.5-turbo

    titles of books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trouble
    -0.75
    undai
    -0.75
     firewall
    -0.75
    æ©
    -0.72
    etooth
    -0.68
     hook
    -0.66
     bloss
    -0.65
     drain
    -0.64
     tremend
    -0.64
     fres
    -0.63
    POSITIVE LOGITS
     Become
    0.92
     Definitive
    0.91
     Reloaded
    0.90
     Volume
    0.84
     Provided
    0.82
     Reborn
    0.82
     Stories
    0.82
     Techniques
    0.81
     Unt
    0.81
     Principles
    0.80
    Act Density 0.106%

    No Known Activations