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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific locations of residence or living situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.17
    omencl
    -0.15
    ÑĢей
    -0.15
    labs
    -0.14
    atz
    -0.14
    ritt
    -0.14
    olls
    -0.14
    holm
    -0.14
    ister
    -0.14
    ahoo
    -0.14
    POSITIVE LOGITS
     habit
    0.16
    icket
    0.14
     presidents
    0.14
    uguay
    0.14
    ernals
    0.14
    ülük
    0.14
    мп
    0.13
     serialVersionUID
    0.13
    QUENCY
    0.13
    BASH
    0.13
    Act Density 0.071%

    No Known Activations