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

    Neuronpedia

    INDEX
    Explanations

    references to sibling relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.19
    idon
    -0.17
    ãĤĴãģĭ
    -0.16
    idal
    -0.16
    _IMPL
    -0.15
    izen
    -0.14
    INCLUDED
    -0.14
    zi
    -0.14
     Himself
    -0.14
     ÙĨÙģسÙĩ
    -0.14
    POSITIVE LOGITS
     themselves
    0.29
     Their
    0.18
    Their
    0.17
    eor
    0.17
     team
    0.17
     collectively
    0.16
     Ñģами
    0.16
     their
    0.16
    dyn
    0.15
     yourselves
    0.15
    Act Density 0.425%

    No Known Activations