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

    Neuronpedia

    INDEX
    Explanations

    words related to writing or scripting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilig
    -0.16
    ainty
    -0.15
    Elapsed
    -0.15
     Kop
    -0.15
    igth
    -0.14
    cape
    -0.14
     troop
    -0.14
    onec
    -0.14
    442
    -0.14
    nown
    -0.14
    POSITIVE LOGITS
    pps
    0.27
    bble
    0.27
    abin
    0.23
    eve
    0.21
    bb
    0.19
    ega
    0.18
    pción
    0.18
     cancell
    0.18
    bd
    0.17
    eg
    0.17
    Act Density 0.006%

    No Known Activations