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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive words referring to ownership or responsibility

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

    Possessive pronouns followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >[]
    -0.56
     član
    -0.52
    WriteLiteral
    -0.50
    ptid
    -0.50
    Rhestr
    -0.50
    offs
    -0.49
    OCCURRED
    -0.48
    แก่
    -0.48
    demies
    -0.46
    身为
    -0.46
    POSITIVE LOGITS
    BagLayout
    0.80
     fault
    0.75
     only
    0.66
     exact
    0.61
     Fault
    0.60
     الرخصة
    0.58
     bedo
    0.58
     idea
    0.58
     liability
    0.57
     idée
    0.57
    Act Density 0.099%

    No Known Activations