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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "forget" and its variations, as well as related phrases about forgetting tasks or information

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

    forgetting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringBootTest
    -0.65
    MediaStore
    -0.39
    kosh
    -0.37
    beitung
    -0.36
     surla
    -0.35
    ADORA
    -0.35
     berhasil
    -0.35
    ())));
    -0.35
    ']))
    -0.35
     InkWell
    -0.34
    POSITIVE LOGITS
    таратура
    0.56
     forgot
    0.55
     ProtoMessage
    0.51
     ब्रेकडाउन
    0.51
     mentioning
    0.50
     evacuate
    0.48
     mention
    0.48
    itespace
    0.46
     forgets
    0.46
    featureID
    0.46
    Act Density 0.016%

    No Known Activations