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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.33
     Therefore
    -0.29
    Therefore
    -0.28
     hence
    -0.26
    æīĢ以
    -0.24
     donc
    -0.23
     consequently
    -0.23
     Hence
    -0.22
    ï¼ĮæīĢ以
    -0.22
     wiÄĻc
    -0.21
    POSITIVE LOGITS
    Alternatively
    0.34
     Alternatively
    0.32
     alternatively
    0.27
     Or
    0.26
     otherwise
    0.26
     or
    0.24
    altern
    0.24
     Otherwise
    0.24
     Altern
    0.23
    .Or
    0.23
    Act Density 0.146%

    No Known Activations