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

    Neuronpedia

    INDEX
    Explanations

    phrases related to keys or important concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.19
    ally
    -0.18
    mul
    -0.17
    ãģĤãĤĬ
    -0.16
    ationToken
    -0.16
    aklı
    -0.16
    arians
    -0.15
    iae
    -0.15
    ±
    -0.15
    ooke
    -0.15
    POSITIVE LOGITS
    hole
    0.22
    note
    0.20
    notes
    0.20
    chains
    0.20
    cloak
    0.19
    eb
    0.19
    nes
    0.19
    ebek
    0.19
    ehir
    0.17
    lings
    0.17
    Act Density 0.061%

    No Known Activations