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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.19
     quindi
    -0.18
     thus
    -0.18
     also
    -0.18
     wiÄĻc
    -0.17
    yet
    -0.17
     ÑĤакже
    -0.17
     ayrıca
    -0.17
     thereby
    -0.17
    also
    -0.17
    POSITIVE LOGITS
     totiž
    0.28
     Firstly
    0.28
     Whereas
    0.24
     Nam
    0.22
     firstly
    0.21
    ãģ¾ãģļ
    0.21
     Instead
    0.20
     namely
    0.20
     instead
    0.20
     whereas
    0.20
    Act Density 0.332%

    No Known Activations