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

    Neuronpedia

    INDEX
    Explanations

    references to early events or stages

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

    "early" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    early life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rmtree
    -0.58
    omiya
    -0.58
     للاسماء
    -0.57
    iastes
    -0.57
     Mercier
    -0.55
    sstream
    -0.52
     ISTAT
    -0.52
    JsonProperty
    -0.52
    bolista
    -0.52
    enumi
    -0.52
    POSITIVE LOGITS
     Early
    1.14
    Early
    1.14
     early
    1.13
     EARLY
    1.11
    early
    1.09
    EARLY
    1.09
     stages
    0.85
    zeitig
    0.84
    Früh
    0.80
     morning
    0.78
    Act Density 0.094%

    No Known Activations