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

    Neuronpedia

    INDEX
    Explanations

    sentences that express opinions or personal experiences

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

    "I", "Me", or other personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    I, All

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Derbyniad
    -0.76
    Personensuche
    -0.73
     nahilalakip
    -0.70
    AndEndTag
    -0.70
    хьтан
    -0.66
     queſta
    -0.65
    出版年
    -0.64
     AssemblyCulture
    -0.63
    UnusedPrivate
    -0.63
     Houſe
    -0.62
    POSITIVE LOGITS
     I
    0.46
    I
    0.45
    S
    0.42
    L
    0.41
    De
    0.40
    Me
    0.40
    Se
    0.39
    TH
    0.39
    IE
    0.39
    Fi
    0.39
    Act Density 0.344%

    No Known Activations