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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific names related to individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckle
    -0.18
    anking
    -0.16
    tics
    -0.15
    incare
    -0.15
    cls
    -0.15
    uples
    -0.15
    iscard
    -0.15
    igger
    -0.15
    uing
    -0.15
    pio
    -0.15
    POSITIVE LOGITS
    iyat
    0.28
    awi
    0.26
    iyah
    0.24
    arat
    0.24
    qa
    0.24
    heed
    0.23
    leh
    0.23
    ayah
    0.23
    noon
    0.22
    noun
    0.22
    Act Density 0.129%

    No Known Activations