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

    Neuronpedia

    INDEX
    Explanations

    phrases related to titles of books, albums, movies or songs

    oai_token-act-pair · gpt-3.5-turbo

    titles or phrases related to cultural works and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warr
    -0.75
    iosyn
    -0.74
     referen
    -0.71
     thous
    -0.69
     satell
    -0.68
    jab
    -0.67
    aditional
    -0.67
    icter
    -0.66
     sidel
    -0.66
     fue
    -0.66
    POSITIVE LOGITS
     Syndrome
    1.17
     Remastered
    1.15
     Volume
    1.07
    âĦ¢
    1.01
     Vol
    0.96
    !,
    0.94
     II
    0.92
     Foundation
    0.92
     Pt
    0.91
     Ratio
    0.87
    Act Density 0.361%

    No Known Activations