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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating advice or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weg
    -0.16
    tbl
    -0.16
    ween
    -0.16
    arger
    -0.16
    ATION
    -0.15
    erd
    -0.14
    esting
    -0.14
    λÏħ
    -0.14
    td
    -0.14
    çľ
    -0.14
    POSITIVE LOGITS
    ster
    0.31
    sters
    0.28
    ple
    0.26
    heet
    0.26
    pler
    0.26
    pling
    0.25
     sheet
    0.22
    otle
    0.22
    ical
    0.22
    pec
    0.22
    Act Density 0.016%

    No Known Activations