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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" indicating excess or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nÃło
    -0.19
     toch
    -0.18
    ron
    -0.17
    st
    -0.16
    reat
    -0.15
    cer
    -0.15
    mp
    -0.15
    wow
    -0.14
    ando
    -0.14
    alone
    -0.14
    POSITIVE LOGITS
    ledo
    0.22
    led
    0.21
    thers
    0.16
    eker
    0.16
    kest
    0.16
    gether
    0.15
    eten
    0.15
    /from
    0.15
    kees
    0.15
    ãģ£ãģ¨
    0.15
    Act Density 0.036%

    No Known Activations