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

    Neuronpedia

    INDEX
    Explanations

    references to early periods or significant shifts in time

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

    "early"

    np_acts-logits-general · gemini-2.0-flash

    early followed by temporal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.65
    netinet
    -0.60
     religieuses
    -0.59
    thansa
    -0.58
     aggiungere
    -0.54
    bolista
    -0.54
     Reiter
    -0.53
    herme
    -0.53
    rmtree
    -0.52
     Westbrook
    -0.52
    POSITIVE LOGITS
    EARLY
    0.96
     EARLY
    0.93
     Early
    0.88
     ISNI
    0.86
    Early
    0.85
     early
    0.85
    early
    0.83
    dawn
    0.78
     continúas
    0.75
     Sett
    0.74
    Act Density 0.084%

    No Known Activations