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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" in various contexts

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

    Said differently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creș
    -0.52
     barbati
    -0.49
     behandeling
    -0.45
    behandlung
    -0.45
     uș
    -0.44
     inversiones
    -0.43
    ßerdem
    -0.43
     frequência
    -0.42
     nisso
    -0.42
     dévelo
    -0.41
    POSITIVE LOGITS
    Said
    1.51
     Said
    1.49
     SAID
    1.13
    said
    0.96
    Says
    0.82
     said
    0.73
     Says
    0.73
    resaid
    0.72
     nakalista
    0.70
    0.60
    Act Density 0.017%

    No Known Activations