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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "ago"

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

    years ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.46
    cheek
    -0.43
    ěr
    -0.42
     nonUne
    -0.41
     Ghi
    -0.40
    mit
    -0.39
     IMDG
    -0.38
    uid
    -0.38
    lech
    -0.38
    cmp
    -0.37
    POSITIVE LOGITS
     years
    0.84
    Years
    0.75
    年前
    0.74
    years
    0.72
     YEARS
    0.70
     années
    0.70
     Years
    0.69
    années
    0.69
    YEARS
    0.68
     Jahren
    0.66
    Act Density 0.008%

    No Known Activations