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

    Neuronpedia

    INDEX
    Explanations

    the word "been" and sometimes the words immediately following.

    oai_token-act-pair · gemini-2.0-flash

    the word 'been'

    np_token-act-pair-logits · gpt-4o-mini

    been

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AsUp
    -0.90
     OMITBAD
    -0.84
     kasarigan
    -0.77
    AntiForgeryToken
    -0.75
    Хьажоргаш
    -0.73
    SBATCH
    -0.70
    Geplaatst
    -0.70
    LookAnd
    -0.69
    ScopeManager
    -0.69
    سطس
    -0.67
    POSITIVE LOGITS
     to
    0.59
     through
    0.59
     Through
    0.52
     THROUGH
    0.47
    Through
    0.47
    Hướng
    0.47
     in
    0.46
    criptive
    0.44
    druk
    0.44
     watching
    0.43
    Act Density 0.299%

    No Known Activations