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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate ease or improvement in processes or experiences

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

    "Makes" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    makes something happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.57
    webElementXpaths
    -0.55
    ########.
    -0.54
    Демографія
    -0.51
     referenties
    -0.51
     noastre
    -0.51
    دانشنامهٔ
    -0.51
     Lordships
    -0.51
     zostać
    -0.50
     enfans
    -0.50
    POSITIVE LOGITS
     it
    1.02
     sure
    0.93
     life
    0.86
    ficult
    0.69
     them
    0.68
     handling
    0.68
     dealing
    0.68
     navigating
    0.67
     finding
    0.66
     learning
    0.66
    Act Density 0.087%

    No Known Activations