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

    Neuronpedia

    INDEX
    Explanations

    references to possession and ownership

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

    one's life or self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tatsache
    -0.48
     pitié
    -0.41
    BrowserModule
    -0.39
    CascadeType
    -0.37
    Поэтому
    -0.36
    Border
    -0.36
    UFACT
    -0.35
    zzleHttp
    -0.35
     problemet
    -0.35
     armado
    -0.34
    POSITIVE LOGITS
     oneself
    0.95
     own
    0.74
     ControllerBase
    0.69
     Ones
    0.68
    Ones
    0.67
     yourself
    0.62
    windowFixed
    0.61
    Personendaten
    0.61
     Италијани
    0.61
     Yourself
    0.61
    Act Density 0.009%

    No Known Activations