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

    Neuronpedia

    INDEX
    Explanations

    frequent use of the definite article "the"

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

    "The [adjective]"

    np_acts-logits-general · gemini-2.0-flash

    only reason or fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.78
    principalColumn
    -0.75
    jsonwebtoken
    -0.75
     Signalez
    -0.70
    wieś
    -0.70
    ManagedBean
    -0.69
     चीज़ों
    -0.69
    XmlAccessType
    -0.69
     <>",
    -0.68
    TextInputLayout
    -0.67
    POSITIVE LOGITS
     only
    1.47
     reason
    1.45
    only
    1.26
     fact
    1.16
     easiest
    1.15
     einzige
    1.06
    zelfde
    1.05
     most
    1.05
     biggest
    1.05
    reason
    1.04
    Act Density 0.756%

    No Known Activations