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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "still."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apro
    -0.15
    rtle
    -0.15
    ed
    -0.15
    ricks
    -0.15
    edBy
    -0.14
    ially
    -0.14
    chts
    -0.14
    chied
    -0.14
    ellen
    -0.14
    QC
    -0.14
    POSITIVE LOGITS
     waters
    0.26
    water
    0.26
    birth
    0.24
    waters
    0.23
    ness
    0.23
     Waters
    0.22
     lifes
    0.20
    born
    0.19
     others
    0.19
    wagon
    0.19
    Act Density 0.016%

    No Known Activations