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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and phrases referencing previous experiences or memories

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

    past times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Already
    -0.56
    already
    -0.52
    Already
    -0.50
     already
    -0.47
    已
    -0.45
    MessageTagHelper
    -0.44
     Desc
    -0.43
     Sudah
    -0.42
    cupa
    -0.42
    已经
    -0.41
    POSITIVE LOGITS
     younger
    0.71
     vroeger
    0.69
     dulu
    0.64
     earlier
    0.60
     früher
    0.57
     vielä
    0.56
     dahulu
    0.56
    earlier
    0.53
     vorige
    0.53
     yore
    0.52
    Act Density 0.046%

    No Known Activations