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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    china
    -0.15
    RouterModule
    -0.15
     Wass
    -0.14
    kin
    -0.14
    ÑģиÑħ
    -0.14
    -suite
    -0.14
    chine
    -0.14
    _simps
    -0.14
    mps
    -0.14
     Vine
    -0.13
    POSITIVE LOGITS
    thers
    0.16
    ivas
    0.15
    arth
    0.15
     воÑĤ
    0.14
    ojis
    0.14
    inda
    0.14
    angl
    0.14
    داÙħ
    0.14
    DL
    0.14
    ters
    0.14
    Act Density 0.165%

    No Known Activations