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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creation or improvement

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

    "Makes" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    makes it easier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    徊
    -0.47
    Rohy
    -0.45
    Aholisi
    -0.41
    énario
    -0.41
     Савезне
    -0.40
     PeEnEo
    -0.39
     мәкал
    -0.38
    السكان
    -0.38
    nosaurus
    -0.38
    ես
    -0.37
    POSITIVE LOGITS
     sure
    0.58
    aarrggbb
    0.47
     ainfi
    0.42
     it
    0.42
    makes
    0.41
     make
    0.40
    =$?
    0.39
     TRABAJO
    0.39
    make
    0.39
    verwijspagina
    0.38
    Act Density 0.113%

    No Known Activations