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

    Neuronpedia

    INDEX
    Explanations

    references to duality or contrasting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENA
    -0.16
    aidu
    -0.16
    Äĩ
    -0.15
    erset
    -0.14
    quip
    -0.14
    ilis
    -0.14
    lyph
    -0.14
    dust
    -0.14
    elsen
    -0.13
    beeld
    -0.13
    POSITIVE LOGITS
     alike
    0.30
     respectively
    0.16
    nel
    0.15
    ious
    0.15
     sides
    0.15
     Scre
    0.15
    umat
    0.15
    å§
    0.14
    rous
    0.14
    ires
    0.14
    Act Density 0.149%

    No Known Activations