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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and informal language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushima
    -0.16
    yled
    -0.15
    velt
    -0.15
    immel
    -0.15
    reb
    -0.14
    chant
    -0.14
    ÅĤaw
    -0.14
    ensburg
    -0.14
    pine
    -0.14
    ellation
    -0.14
    POSITIVE LOGITS
    олоÑĤ
    0.16
    olumn
    0.15
     punct
    0.15
    tte
    0.14
     Townsend
    0.14
     volta
    0.14
    nds
    0.14
     LIC
    0.14
     [|
    0.14
     Tribe
    0.14
    Act Density 0.060%

    No Known Activations