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

    Neuronpedia

    INDEX
    Explanations

    key terms related to specific techniques, processes, and measurements in various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ones
    -0.15
     Malk
    -0.15
     Conserv
    -0.14
    aný
    -0.14
    ophil
    -0.13
    dess
    -0.13
    ONES
    -0.13
    KA
    -0.13
    маз
    -0.13
    nos
    -0.12
    POSITIVE LOGITS
    948
    0.16
    angelo
    0.14
    çĸ
    0.14
    867
    0.14
    inç
    0.14
     Sov
    0.13
    797
    0.13
     Lov
    0.13
    iap
    0.13
     meg
    0.13
    Act Density 0.440%

    No Known Activations