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

    Neuronpedia

    INDEX
    Explanations

    terms associated with family, child, and user-friendly content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.44
     Paglinawan
    -0.40
    tagHelperRunner
    -0.38
    EndInit
    -0.38
    はじめに
    -0.38
     мәкал
    -0.37
    MessageOf
    -0.36
    SharedCtor
    -0.36
    RTSN
    -0.35
     vermittelt
    -0.35
    POSITIVE LOGITS
     friendly
    2.80
    friendly
    2.44
     Friendly
    2.39
    Friendly
    2.28
     friendliness
    1.96
     FRIEND
    1.91
     unfriendly
    1.82
    FRIEND
    1.73
    友好
    1.57
    vriende
    1.57
    Act Density 0.197%

    No Known Activations