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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beck
    -0.16
    ull
    -0.15
    íİ
    -0.15
    wers
    -0.15
    573
    -0.15
    .dtd
    -0.15
    ille
    -0.15
    amp
    -0.15
    roid
    -0.15
    lice
    -0.15
    POSITIVE LOGITS
     Leaving
    0.18
     leaving
    0.17
    yleft
    0.15
    leave
    0.15
    LTRB
    0.15
    SED
    0.15
    amerate
    0.15
    togroup
    0.15
     leave
    0.15
    kker
    0.14
    Act Density 0.278%

    No Known Activations