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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate hierarchy, ownership, or relationship descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hn
    -0.16
     пÑĢоÑĩ
    -0.16
    åĬŁ
    -0.15
    PointF
    -0.15
    aeper
    -0.14
    hud
    -0.14
    маг
    -0.14
    rys
    -0.14
    ideo
    -0.14
    ulin
    -0.14
    POSITIVE LOGITS
     whom
    0.28
     sorts
    0.20
    اÙĨ
    0.18
     circumstance
    0.17
     stature
    0.17
     all
    0.16
     change
    0.16
    ë¥ĺ
    0.15
     destiny
    0.15
     xứ
    0.15
    Act Density 0.181%

    No Known Activations