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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" and its variations in different contexts

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

    Follows the word "say"

    np_acts-logits-general · gemini-2.0-flash

    saying things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagHelpers
    -0.61
    出版年
    -0.58
     StringVar
    -0.55
    foundland
    -0.55
    fullWidth
    -0.54
    rstrip
    -0.52
    AndEndTag
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    tagHelperRunner
    -0.51
    AutoField
    -0.50
    POSITIVE LOGITS
     goodbye
    1.02
     Say
    0.76
     hello
    0.76
     SAY
    0.75
     things
    0.73
    Say
    0.72
    SAY
    0.64
     مشين
    0.61
    er
    0.60
    goodbye
    0.59
    Act Density 0.104%

    No Known Activations