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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and references to statistical thresholds or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wider
    -0.53
     quedo
    -0.49
     bolt
    -0.48
    bkz
    -0.48
     OMITBAD
    -0.47
    ongiorno
    -0.47
    egl
    -0.47
    Mvh
    -0.47
     Familienname
    -0.47
     Faster
    -0.47
    POSITIVE LOGITS
    awtextra
    0.81
     estimated
    0.81
    basicConfig
    0.74
    EndContext
    0.74
     amount
    0.73
    kháu
    0.73
     average
    0.71
     ſmall
    0.71
    Демографія
    0.70
    ISupport
    0.69
    Act Density 2.847%

    No Known Activations