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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the notion of additional information or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rum
    -0.17
    run
    -0.17
    sel
    -0.17
    owi
    -0.16
    sc
    -0.16
    ulated
    -0.16
    ified
    -0.16
    sen
    -0.15
    sci
    -0.15
    ulatory
    -0.14
    POSITIVE LOGITS
    ance
    0.34
    ing
    0.31
     ado
    0.29
    most
    0.26
    ed
    0.26
    -reaching
    0.24
    -more
    0.22
    hin
    0.22
    ANCE
    0.21
    MORE
    0.21
    Act Density 0.025%

    No Known Activations