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

    Neuronpedia

    INDEX
    Explanations

    expressions of speech or quotation

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

    Follows forms of the word "say."

    np_acts-logits-general · gemini-2.0-flash

    say that or anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aiheesta
    -0.73
    évaluateur
    -0.68
     houſe
    -0.64
     nahilalakip
    -0.63
     <<<<<<<<<<<<<<
    -0.60
    ſelf
    -0.60
     Mainland
    -0.60
     greateſt
    -0.59
     austral
    -0.59
     />";
    -0.59
    POSITIVE LOGITS
     goodbye
    1.21
     hello
    0.95
     yes
    0.80
     nothing
    0.74
    goodbye
    0.72
    er
    0.70
     farewell
    0.70
     thank
    0.69
     prayers
    0.64
     aloud
    0.63
    Act Density 0.087%

    No Known Activations