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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isci
    -0.19
    inci
    -0.16
    onn
    -0.15
    embed
    -0.15
    361
    -0.15
    inea
    -0.15
    ÙĪتÛĮ
    -0.15
    ongan
    -0.14
    iera
    -0.14
    обов
    -0.14
    POSITIVE LOGITS
    ussy
    0.17
    erland
    0.16
    acker
    0.16
     Ih
    0.15
    .nd
    0.14
    nds
    0.14
     Morales
    0.14
    inç
    0.14
     Ain
    0.14
     CES
    0.13
    Act Density 0.100%

    No Known Activations