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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

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

    Salutations (e.g., "Hi [Name]")

    np_acts-logits-general · gemini-2.0-flash

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.99
    oredCriteria
    -0.91
    gridy
    -0.87
    省市镇
    -0.87
    SequentialGroup
    -0.86
    EDEFAULT
    -0.84
    TintMode
    -0.84
    SourceChecksum
    -0.84
    )++;
    -0.82
    ]")]
    -0.80
    POSITIVE LOGITS
     who
    0.65
     aka
    0.55
     K
    0.54
     whom
    0.53
     G
    0.53
     @
    0.51
     from
    0.50
     our
    0.49
     M
    0.48
     B
    0.47
    Act Density 0.130%

    No Known Activations