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

    Neuronpedia

    INDEX
    Explanations

    references to speech or statements made in the text

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

    "say" or variants

    np_acts-logits-general · gemini-2.0-flash

    saying something or being said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']")
    -0.67
     Malte
    -0.66
    `]
    -0.66
    ㅋㅋ
    -0.64
     Staub
    -0.63
     <<<<<<<<<<<<<<
    -0.61
    TagHelpers
    -0.61
    Dez
    -0.60
    Архівовано
    -0.59
     URB
    -0.59
    POSITIVE LOGITS
     Say
    1.19
     SAY
    1.14
    SAY
    1.09
    Say
    1.07
     say
    1.04
    say
    1.00
     Says
    0.96
     says
    0.93
     goodbye
    0.89
     SAYS
    0.88
    Act Density 0.098%

    No Known Activations