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

    Neuronpedia

    INDEX
    Explanations

    phrases that include variations of the word "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Staub
    -0.76
    urel
    -0.71
    ']")
    -0.67
    ".$_
    -0.67
    Składniki
    -0.65
    وردار
    -0.65
    BibitemOpen
    -0.64
    NOSTIC
    -0.64
     گرد
    -0.64
    bibfield
    -0.63
    POSITIVE LOGITS
     say
    2.81
     SAY
    2.62
    say
    2.62
     Say
    2.60
    Say
    2.60
    SAY
    2.38
     Saying
    2.17
     saying
    2.10
     says
    2.07
    saying
    2.00
    Act Density 0.069%

    No Known Activations