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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate formal reporting or official statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kyt
    -0.15
    .localized
    -0.15
    arius
    -0.15
    roj
    -0.14
     kli
    -0.14
     GiỼi
    -0.14
    PCP
    -0.14
     Fro
    -0.14
    esting
    -0.14
    arma
    -0.14
    POSITIVE LOGITS
    ailles
    0.14
    vr
    0.14
    èĩ£
    0.14
    INES
    0.14
    สม
    0.14
     gradu
    0.14
    iese
    0.14
     Overse
    0.13
     stump
    0.13
     medi
    0.13
    Act Density 0.060%

    No Known Activations