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

    Neuronpedia

    INDEX
    Explanations

    technical terms and methodologies related to algorithmic processes and system behavior analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adir
    -0.17
     dohod
    -0.15
     Frost
    -0.14
    Biz
    -0.13
     Sabbath
    -0.13
     Freeze
    -0.13
    uras
    -0.13
    ziel
    -0.13
    .spy
    -0.13
    .Microsoft
    -0.13
    POSITIVE LOGITS
     Bay
    0.33
     uncertainty
    0.32
     posterior
    0.31
     Unc
    0.30
    Bay
    0.30
     uncertainties
    0.28
     uncertain
    0.28
     uncert
    0.26
    unc
    0.25
    Unc
    0.24
    Act Density 0.020%

    No Known Activations