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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and exchanges in collaborative contexts

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

    the more, the more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beſch
    -0.70
    niſſe
    -0.70
     kasarigan
    -0.69
     mijne
    -0.65
     laſſen
    -0.65
    iſchen
    -0.63
    RegressionTest
    -0.63
     miniaturka
    -0.62
     zijne
    -0.62
    TestingModule
    -0.62
    POSITIVE LOGITS
    base
    0.35
    !
    0.33
    Больше
    0.33
     nakalista
    0.33
    column
    0.32
     column
    0.30
    ater
    0.30
    Base
    0.28
    better
    0.28
     Yo
    0.28
    Act Density 0.021%

    No Known Activations