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

    Neuronpedia

    INDEX
    Explanations

    the word "too" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toch
    -0.18
     nÃło
    -0.18
    st
    -0.16
    iny
    -0.15
    ry
    -0.15
    ullo
    -0.15
    pu
    -0.15
    idae
    -0.15
    ful
    -0.14
    core
    -0.14
    POSITIVE LOGITS
    led
    0.25
    ledo
    0.20
    /from
    0.20
     boot
    0.19
    gether
    0.18
    ůr
    0.17
    o
    0.16
    thers
    0.15
    orado
    0.15
    ths
    0.15
    Act Density 0.025%

    No Known Activations