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

    Neuronpedia

    INDEX
    Explanations

    references to groups or categories of individuals or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Each" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    each followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anything
    -0.46
     li
    -0.43
    (!(
    -0.42
     never
    -0.42
     hiç
    -0.41
    never
    -0.41
    //
    -0.41
    追
    -0.40
    kot
    -0.40
    INO
    -0.40
    POSITIVE LOGITS
     individually
    1.31
     câte
    1.24
     separately
    1.23
     each
    1.03
     Each
    1.01
     einzeln
    0.99
     independently
    0.99
    Each
    0.98
     EACH
    0.96
    each
    0.95
    Act Density 0.338%

    No Known Activations