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

    Neuronpedia

    INDEX
    Explanations

    references to past events and changes in status or conditions regarding political and social topics

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

    "Used to" or similar past tense phrases

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bientôt
    -0.90
     diesmal
    -0.89
     henceforth
    -0.87
     mittlerweile
    -0.85
     uiteindelijk
    -0.84
     inzwischen
    -0.84
     inmiddels
    -0.83
     finally
    -0.82
     subsequently
    -0.81
     désormais
    -0.81
    POSITIVE LOGITS
     thought
    0.66
    以為
    0.58
     feared
    0.57
    thought
    0.55
     considered
    0.54
     believed
    0.53
     notion
    0.52
    以为
    0.52
    といえば
    0.52
    était
    0.52
    Act Density 0.375%

    No Known Activations