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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interest and engagement in various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to legal agreements and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interesting and well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interest
    -0.99
     interesting
    -0.97
    interesting
    -0.91
    interest
    -0.86
     interests
    -0.84
     INTEREST
    -0.81
     Interesting
    -0.80
     Interest
    -0.80
    Interesting
    -0.79
    interests
    -0.77
    POSITIVE LOGITS
     utafitiHapana
    0.88
    Kjelder
    0.79
    MENAFN
    0.79
    
    0.74
     архивлан
    0.72
    yntaxException
    0.70
    survival
    0.69
     auffi
    0.69
     survival
    0.69
     ſever
    0.68
    Act Density 0.034%

    No Known Activations