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

    Neuronpedia

    INDEX
    Explanations

    references to uniqueness or exceptionalism in various contexts

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

    "No one" or negation

    np_acts-logits-general · gemini-2.0-flash

    No one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sometimes
    -0.52
     also
    -0.48
     тоже
    -0.46
     only
    -0.45
    also
    -0.44
     tiež
    -0.44
    ConfigureAwait
    -0.43
     també
    -0.43
    sometimes
    -0.41
    ěk
    -0.41
    POSITIVE LOGITS
     ever
    1.25
     EVER
    1.13
    Ever
    0.98
     Ever
    0.98
     jemals
    0.94
    ever
    0.88
     تانيه
    0.85
     dared
    0.83
    EVER
    0.83
     truly
    0.82
    Act Density 0.219%

    No Known Activations