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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dn
    -0.17
    eln
    -0.17
    AGO
    -0.16
    oval
    -0.15
    izer
    -0.15
    eyle
    -0.14
    arus
    -0.13
    ä»ĺãģij
    -0.13
    ushi
    -0.13
    rette
    -0.13
    POSITIVE LOGITS
     about
    0.26
     information
    0.22
    about
    0.20
     info
    0.19
     detail
    0.18
    information
    0.18
     ways
    0.18
     details
    0.17
    reason
    0.17
     información
    0.16
    Act Density 0.012%

    No Known Activations