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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rankings or top choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enko
    -0.15
    .Align
    -0.15
     Beste
    -0.14
    esson
    -0.14
    esses
    -0.14
     Nin
    -0.14
    y
    -0.14
    ãĥķãĥĪ
    -0.14
    lew
    -0.14
    nce
    -0.14
    POSITIVE LOGITS
    -notch
    0.21
    -rated
    0.20
    erval
    0.18
    -selling
    0.18
    pling
    0.17
     performing
    0.17
     rated
    0.16
    ech
    0.16
    pest
    0.16
    ography
    0.15
    Act Density 0.025%

    No Known Activations