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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of proper nouns in a list-like format, often associated with significant individuals or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Characters
    -0.71
    Decre
    -0.66
    lly
    -0.65
    alities
    -0.63
    Compat
    -0.63
    pled
    -0.60
    CONCLUS
    -0.60
     increments
    -0.60
    Compare
    -0.59
    atta
    -0.58
    POSITIVE LOGITS
     founder
    1.03
     aka
    1.02
     Jr
    0.95
     pictured
    0.92
     president
    0.91
     dean
    0.89
     chairman
    0.88
    founder
    0.88
     PhD
    0.88
     CEO
    0.87
    Act Density 0.116%

    No Known Activations