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

    Neuronpedia

    INDEX
    Explanations

    terms related to archiving and collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =""><
    -0.57
     estr
    -0.53
    ThemeProvider
    -0.52
    hilation
    -0.51
    HttpStatus
    -0.50
    IntoConstraints
    -0.49
     CET
    -0.49
    prime
    -0.47
     surla
    -0.47
    Tij
    -0.47
    POSITIVE LOGITS
     archive
    1.22
     Archive
    1.15
     Archives
    1.10
     archives
    1.09
     harvests
    0.96
    Archives
    0.96
    Archive
    0.95
     archived
    0.93
     harvest
    0.91
     Harvesting
    0.88
    Act Density 0.076%

    No Known Activations