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

    Neuronpedia

    INDEX
    Explanations

    phrases and variations of the verb "say" in different contexts

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

    saying something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.50
     Fres
    -0.48
     Bim
    -0.47
     Moose
    -0.47
     McLeod
    -0.47
     Mons
    -0.46
     MCS
    -0.46
     Vac
    -0.45
    _{\
    -0.45
     KAB
    -0.45
    POSITIVE LOGITS
    say
    1.10
    Say
    1.02
     say
    1.02
     SAY
    1.00
     Say
    0.99
    SAY
    0.90
    says
    0.85
     SAYS
    0.82
     sayin
    0.79
     says
    0.79
    Act Density 0.015%

    No Known Activations