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

    Neuronpedia

    INDEX
    Explanations

    references to durations of time, particularly years and months

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

    Time periods (years, months) followed by "ago," "later," or "from."

    np_acts-logits-general · gemini-2.0-flash

    years ago or months later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -1.21
     Jefus
    -1.11
     myſelf
    -1.08
     pleaſure
    -1.07
     Theſe
    -1.05
     themſelves
    -1.03
     fubject
    -1.03
     itſelf
    -1.02
     himſelf
    -1.01
     ſtate
    -1.00
    POSITIVE LOGITS
     ago
    0.66
     later
    0.63
     after
    0.53
     hence
    0.53
    ごと
    0.47
    isOk
    0.44
     younger
    0.44
     el
    0.43
     faster
    0.42
     earlier
    0.41
    Act Density 0.132%

    No Known Activations