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

    Neuronpedia

    INDEX
    Explanations

    discussions or analyses involving comparisons and evaluations

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

    Comparison or impact of something

    np_acts-logits-general · gemini-2.0-flash

    how something compares or relates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.54
    entibus
    -0.51
     consac
    -0.47
    有個
    -0.47
     soulign
    -0.46
    __':
    -0.46
     incluem
    -0.46
     clairement
    -0.46
    JoinTable
    -0.45
     immediatamente
    -0.45
    POSITIVE LOGITS
     fared
    1.07
     relates
    1.03
     compares
    1.02
     relate
    1.02
     affects
    0.99
     interacts
    0.98
     interact
    0.96
     differs
    0.91
     reacts
    0.91
     compare
    0.90
    Act Density 0.203%

    No Known Activations