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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    oai_token-act-pair · gpt-3.5-turbo

    titles of movies and their related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elong
    -0.85
    UTC
    -0.68
    policy
    -0.66
     credential
    -0.66
    usual
    -0.66
     referen
    -0.65
     shenan
    -0.64
    undai
    -0.64
    amen
    -0.63
    rane
    -0.63
    POSITIVE LOGITS
     Trilogy
    1.35
     trilogy
    1.29
     Remastered
    1.22
     Chronicles
    1.11
     soundtrack
    1.11
     Reloaded
    1.10
     Unch
    1.07
     Redux
    1.07
     starring
    1.04
     novels
    0.99
    Act Density 0.252%

    No Known Activations