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

    Neuronpedia

    INDEX
    Explanations

    sentences that include numerical values or monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dent
    -0.15
     Peg
    -0.15
    721
    -0.15
    jn
    -0.15
    ouden
    -0.14
    metic
    -0.14
    .CodeAnalysis
    -0.13
     Pent
    -0.13
    pack
    -0.13
     whe
    -0.13
    POSITIVE LOGITS
    iox
    0.16
    лий
    0.15
    imore
    0.15
    utsch
    0.15
    usk
    0.14
    icari
    0.14
    ogg
    0.14
     Readonly
    0.14
    LEC
    0.14
    åĥ¹
    0.14
    Act Density 0.038%

    No Known Activations