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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate personal decisions or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Viited
    -0.54
    Livro
    -0.51
     abusers
    -0.50
     pinulongan
    -0.50
    Kjelder
    -0.47
    LIBRARY
    -0.46
     innocently
    -0.44
     langage
    -0.44
    Bibliograf
    -0.44
    ことができました
    -0.44
    POSITIVE LOGITS
     decided
    1.46
     decide
    1.30
     decides
    1.28
    decided
    1.25
    Decide
    1.24
     Decide
    1.23
    decide
    1.19
     deciding
    1.15
     Decided
    1.15
    Decided
    1.05
    Act Density 0.140%

    No Known Activations