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

    Neuronpedia

    INDEX
    Explanations

    the word "too" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nÃło
    -0.16
    pu
    -0.15
    mp
    -0.15
    brook
    -0.15
    course
    -0.15
    kar
    -0.15
    kker
    -0.15
    ullo
    -0.15
    walk
    -0.14
    ogne
    -0.14
    POSITIVE LOGITS
    gether
    0.22
    /from
    0.20
    led
    0.18
    thers
    0.18
    ledo
    0.17
    kest
    0.17
    o
    0.17
    oot
    0.15
    eko
    0.15
    ichni
    0.15
    Act Density 0.028%

    No Known Activations