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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating evaluation and comparison of performance or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .LoggerFactory
    -0.15
     Maple
    -0.15
    OWL
    -0.14
    IDA
    -0.14
    iyon
    -0.14
    acity
    -0.14
    wij
    -0.14
    wig
    -0.13
    abor
    -0.13
    磨
    -0.13
    POSITIVE LOGITS
    óc
    0.14
     ãĥĽ
    0.14
     Cards
    0.13
    uras
    0.13
    ãģķãĤĵãģ®
    0.13
    strap
    0.13
    ième
    0.13
    MBProgressHUD
    0.13
    eyh
    0.13
     Hills
    0.13
    Act Density 0.104%

    No Known Activations