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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and personal experiences related to family

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

    first-person singular pronouns and references to personal experiences or opinions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.47
    layoutControl
    -0.40
    uParam
    -0.39
    StructField
    -0.38
     noms
    -0.38
     overall
    -0.38
     Mancini
    -0.37
     Гон
    -0.37
     Overall
    -0.37
    featureID
    -0.37
    POSITIVE LOGITS
     myself
    0.68
     personally
    0.60
     often
    0.58
     spesso
    0.57
    +#+
    0.57
    myself
    0.57
    เคย
    0.54
    我自己
    0.54
     ourselves
    0.54
     kiedyś
    0.54
    Act Density 0.437%

    No Known Activations