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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     olsa
    -0.18
    ereotype
    -0.18
    ount
    -0.16
    lette
    -0.15
    ark
    -0.14
    ÌĪ
    -0.14
    icom
    -0.14
    ç»Ń
    -0.14
    ery
    -0.14
    ildo
    -0.14
    POSITIVE LOGITS
    ably
    0.22
    INDER
    0.17
     unde
    0.15
    ableView
    0.14
    ances
    0.14
    iable
    0.14
    ABLE
    0.14
     fren
    0.14
    fully
    0.13
    /value
    0.13
    Act Density 0.020%

    No Known Activations