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

    Neuronpedia

    INDEX
    Explanations

    comparisons emphasizing similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eced
    -0.16
    ernel
    -0.16
    irts
    -0.15
    ustain
    -0.15
    gaard
    -0.15
    ÑĨей
    -0.14
    erten
    -0.14
    instein
    -0.14
    cak
    -0.14
    ARRANT
    -0.14
    POSITIVE LOGITS
    sembl
    0.20
     nhau
    0.20
    hen
    0.18
    sembled
    0.17
    sembler
    0.17
     they
    0.17
    sembles
    0.17
    phy
    0.16
     having
    0.16
    seg
    0.15
    Act Density 0.045%

    No Known Activations