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

    Neuronpedia

    INDEX
    Explanations

    references to objects, particularly in a formal or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kraj
    -0.19
    ÑĤаб
    -0.15
    ptions
    -0.15
    chner
    -0.15
    AILS
    -0.14
    amoto
    -0.14
    961
    -0.13
    ASET
    -0.13
    Ù
    -0.13
    alli
    -0.13
    POSITIVE LOGITS
     Aware
    0.15
    ambi
    0.15
    verse
    0.15
    lique
    0.14
    義
    0.14
    roti
    0.14
    ILLS
    0.14
    æĪ
    0.14
    noon
    0.14
    agnet
    0.14
    Act Density 0.006%

    No Known Activations