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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" and its variations used for emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cert
    -0.07
    eer
    -0.07
    yx
    -0.06
    empt
    -0.06
    xn
    -0.06
    IDS
    -0.06
    293
    -0.06
    йн
    -0.06
    oders
    -0.05
    chter
    -0.05
    POSITIVE LOGITS
    late
    0.10
     late
    0.09
     Late
    0.09
    led
    0.09
    jours
    0.09
    Late
    0.08
    orm
    0.08
    ledo
    0.07
    obraz
    0.07
     Young
    0.07
    Act Density 0.013%

    No Known Activations