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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.14
    oir
    -0.14
    ury
    -0.14
    اÙĦÙĥ
    -0.14
    ÏĥÏĨα
    -0.14
    bao
    -0.14
    jerne
    -0.14
    空
    -0.13
    odal
    -0.13
    UsageId
    -0.13
    POSITIVE LOGITS
    rets
    0.18
     Rogers
    0.16
     Wen
    0.15
     Too
    0.14
    li
    0.14
    isti
    0.14
    e
    0.14
     wo
    0.14
    ret
    0.14
     much
    0.14
    Act Density 0.026%

    No Known Activations