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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thirty" in different contexts

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

    thirty followed by a unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     setShow
    -0.56
    nup
    -0.53
    Coop
    -0.50
    Innov
    -0.50
    coop
    -0.49
     landslide
    -0.48
     synapse
    -0.48
     Inoc
    -0.47
    laway
    -0.47
    voting
    -0.47
    POSITIVE LOGITS
     Thirty
    1.26
    thirty
    1.22
     thirty
    1.21
    Thirty
    1.20
     treinta
    0.91
     THIR
    0.90
     thirties
    0.89
     trente
    0.89
    三十
    0.86
    3
    0.75
    Act Density 0.009%

    No Known Activations