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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collective actions or observations by the authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.23
     Jefus
    -1.14
     Theſe
    -1.12
    extAlignment
    -0.97
     ſeveral
    -0.96
     faſt
    -0.93
     Monfieur
    -0.91
    >\<^
    -0.91
     itſelf
    -0.90
     photolibrary
    -0.90
    POSITIVE LOGITS
     use
    0.62
     also
    0.60
     구
    0.52
     try
    0.51
    次に
    0.49
     acque
    0.48
     then
    0.48
     note
    0.47
     find
    0.47
     a
    0.47
    Act Density 0.569%

    No Known Activations