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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erse
    -0.17
    ãĤ¤ãĥ³ãĥĪ
    -0.16
    ers
    -0.16
    erry
    -0.15
    èm
    -0.15
     supposed
    -0.15
    ed
    -0.14
    ãĢĤãĢĤ↵↵
    -0.14
    embers
    -0.14
    ishly
    -0.14
    POSITIVE LOGITS
    eview
    0.17
    -bodied
    0.17
    -plugins
    0.16
    ehir
    0.16
    rosse
    0.15
    ooke
    0.15
    REFERRED
    0.15
    SSID
    0.15
    WindowState
    0.15
    atır
    0.14
    Act Density 0.055%

    No Known Activations