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

    Neuronpedia

    INDEX
    Explanations

    terms indicating significant changes or impacts

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

    change and decisive moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Riding
    -0.39
     سبيل
    -0.37
    üht
    -0.35
    listBox
    -0.35
    }{||
    -0.33
    ellido
    -0.32
     Willing
    -0.32
     forsø
    -0.32
     Bem
    -0.31
    ikkert
    -0.31
    POSITIVE LOGITS
    changer
    1.18
     changer
    1.08
     Changer
    1.04
    changers
    0.98
    Changer
    0.90
     chang
    0.71
     breakthrough
    0.66
     decisivo
    0.66
     GenerationType
    0.61
     breakthroughs
    0.60
    Act Density 0.004%

    No Known Activations