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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ±Ð¾ÑĤ
    -0.14
    ÑĦÑĦ
    -0.14
    Ñģли
    -0.14
    oris
    -0.14
    iyat
    -0.14
    xmax
    -0.14
     Männer
    -0.14
    vos
    -0.13
    reserve
    -0.13
    era
    -0.13
    POSITIVE LOGITS
     rim
    0.18
     Rim
    0.16
    mere
    0.15
    eam
    0.14
     Pit
    0.14
    eshire
    0.14
    encil
    0.14
     worse
    0.14
    ird
    0.14
    elines
    0.14
    Act Density 0.090%

    No Known Activations