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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change in status or perception

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

    really + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.59
    UnitTesting
    -0.56
    penup
    -0.52
     kaarangay
    -0.47
    Externé
    -0.45
    ViewFeatures
    -0.45
     rainha
    -0.45
     Bruch
    -0.43
    ſel
    -0.42
    rupal
    -0.42
    POSITIVE LOGITS
     really
    1.22
    really
    1.16
     Really
    1.14
    Really
    1.11
     realmente
    1.07
     REALLY
    1.02
     vraiment
    0.94
     truly
    0.91
     wirklich
    0.85
    truly
    0.84
    Act Density 0.066%

    No Known Activations