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

    Neuronpedia

    INDEX
    Explanations

    words that end in the suffix "ent" or are related to the concept of being an agent or having a role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.22
    keit
    -0.19
    bers
    -0.18
    Ùĩ
    -0.18
    sut
    -0.17
    र
    -0.16
    heads
    -0.16
    pline
    -0.16
    sites
    -0.15
    sense
    -0.15
    POSITIVE LOGITS
    ech
    0.33
    ertainment
    0.28
    ucky
    0.27
    emente
    0.26
    ennial
    0.25
    ention
    0.24
    eb
    0.24
    rop
    0.24
    oon
    0.23
    ropy
    0.23
    Act Density 0.170%

    No Known Activations