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

    Neuronpedia

    INDEX
    Explanations

    topics related to decision-making and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inse
    -0.15
    shaw
    -0.15
    WARE
    -0.14
    bh
    -0.13
    Expired
    -0.13
    atsu
    -0.13
    nbsp
    -0.13
     landmark
    -0.13
    enti
    -0.13
    bins
    -0.13
    POSITIVE LOGITS
    baugh
    0.17
    oba
    0.16
    á»ij
    0.15
    ubar
    0.15
    ompiler
    0.14
    충
    0.14
    igel
    0.14
    åŃĿ
    0.14
    eya
    0.13
     Till
    0.13
    Act Density 0.376%

    No Known Activations