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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of creating or producing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UME
    -0.16
    wyn
    -0.16
    nid
    -0.16
    quo
    -0.15
    uality
    -0.15
    ncia
    -0.15
    cribe
    -0.15
    scri
    -0.15
    uit
    -0.14
    neau
    -0.14
    POSITIVE LOGITS
     sure
    0.44
    leine
    0.36
     sense
    0.31
    -bel
    0.25
     Sure
    0.24
    Sure
    0.23
     use
    0.22
     headlines
    0.21
    sure
    0.21
    -up
    0.20
    Act Density 0.173%

    No Known Activations