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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "however."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amu
    -0.15
    بار
    -0.15
    sx
    -0.14
    sst
    -0.14
    ighth
    -0.14
    inqu
    -0.14
    nyder
    -0.14
    rell
    -0.13
    endale
    -0.13
    olib
    -0.13
    POSITIVE LOGITS
    ,
    0.20
     briefly
    0.18
    Äĥ
    0.17
    eum
    0.16
     fleet
    0.16
    jak
    0.15
     tempting
    0.15
    eday
    0.14
    onth
    0.14
     slight
    0.14
    Act Density 0.044%

    No Known Activations