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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating completeness or newness in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    light
    -0.18
    elin
    -0.16
    ses
    -0.15
     ç¸
    -0.15
    dao
    -0.15
    ä¸ĩ
    -0.14
    prises
    -0.14
    èIJ¬
    -0.14
    ÐĿаÑģ
    -0.14
    holm
    -0.14
    POSITIVE LOGITS
    heart
    0.33
    -hearted
    0.25
     lot
    0.23
    meal
    0.23
    /part
    0.22
    -sale
    0.21
    foods
    0.21
     bunch
    0.20
     host
    0.19
     Foods
    0.19
    Act Density 0.026%

    No Known Activations