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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conclusions, evaluations, or significant factors in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eneuve
    -0.38
     wyboru
    -0.37
     weekdays
    -0.36
    envolvimento
    -0.35
    CHOICE
    -0.34
     choice
    -0.32
     Lewis
    -0.32
     bune
    -0.32
     Choice
    -0.32
     oznac
    -0.32
    POSITIVE LOGITS
     BoxFit
    0.66
    AsUp
    0.52
     كومونز
    0.48
     الرياضيه
    0.48
    WaitGroup
    0.47
    PerformLayout
    0.47
    ьаж
    0.46
    Spoljašnje
    0.46
    Übernach
    0.46
    rrggbb
    0.46
    Act Density 1.386%

    No Known Activations