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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and clauses dependent on context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ault
    -0.18
    isposable
    -0.16
    sey
    -0.15
    edBy
    -0.15
    ayar
    -0.15
    orch
    -0.14
    erty
    -0.14
    atty
    -0.14
     knull
    -0.14
    .sap
    -0.14
    POSITIVE LOGITS
     or
    0.33
     или
    0.25
    æĪĸèĢħ
    0.25
     æĪĸ
    0.23
     atau
    0.22
     oder
    0.22
     ëĺIJëĬĶ
    0.22
     nebo
    0.22
     або
    0.21
    æĪĸ
    0.21
    Act Density 0.140%

    No Known Activations