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

    Neuronpedia

    INDEX
    Explanations

    specific phrases that involve measurements or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderingContext
    -0.16
    Bid
    -0.16
    ahn
    -0.15
    aña
    -0.15
    ilim
    -0.15
    antee
    -0.15
     Bid
    -0.14
    chner
    -0.14
    dda
    -0.14
    reon
    -0.14
    POSITIVE LOGITS
    clerosis
    0.15
    odu
    0.14
    ouston
    0.14
    Ø°ÙĬ
    0.14
     Driver
    0.14
     Dorm
    0.14
    olk
    0.14
    omatic
    0.13
     Favor
    0.13
    pdev
    0.13
    Act Density 2.025%

    No Known Activations