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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "he"

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

    he said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.50
     nonUne
    -0.49
    ConstraintMaker
    -0.48
     PeEnEo
    -0.46
    acias
    -0.45
     propOrder
    -0.45
    LookAnd
    -0.45
     AssemblyProduct
    -0.44
    uta
    -0.44
    jsii
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.56
    DoubleQuotes
    0.51
    enterOuterAlt
    0.44
     insuffisamment
    0.44
     때문
    0.42
    Hentet
    0.40
    Tikang
    0.39
    ิลปะ
    0.38
    itattu
    0.38
     المعيارى
    0.37
    Act Density 0.004%

    No Known Activations