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

    Neuronpedia

    INDEX
    Explanations

    references to software versioning and assembly attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.45
    VersionUID
    -0.44
     Harms
    -0.38
    UserScript
    -0.37
    ber
    -0.36
     Regret
    -0.36
     exiles
    -0.36
    flakes
    -0.35
    aban
    -0.35
    älte
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    1.47
     queſta
    0.77
     ſind
    0.70
    хьтан
    0.68
    Demografie
    0.66
     nahilalakip
    0.65
    ſelf
    0.65
    Хьажоргаш
    0.64
    rungsseite
    0.63
     pleaſure
    0.61
    Act Density 0.000%

    No Known Activations