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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" and its variations, indicating reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "said" and a pronoun

    np_acts-logits-general · gemini-2.0-flash

    said that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }^{\
    -0.47
    ^{\
    -0.45
    otriva
    -0.44
    pholes
    -0.44
    randomUUID
    -0.44
     וח
    -0.41
     ^{\
    -0.41
    はずです
    -0.41
     Partially
    -0.41
    上的
    -0.41
    POSITIVE LOGITS
     goodbye
    0.56
    出版年
    0.54
     שוליים
    0.53
    PropertyChanging
    0.46
    GOTREF
    0.45
     AttributeSet
    0.45
    DockStyle
    0.45
    setContentView
    0.44
     lenker
    0.43
    UnusedPrivate
    0.42
    Act Density 0.088%

    No Known Activations