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

    Neuronpedia

    INDEX
    Explanations

    proper names, with a specific emphasis on the name "Helen"

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals and organizations, particularly "Helen" and "JPMorgan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebels
    -0.79
    arro
    -0.76
    arthed
    -0.75
    asted
    -0.75
    nir
    -0.74
    igators
    -0.74
    andi
    -0.74
    agen
    -0.73
    aid
    -0.73
    Rated
    -0.72
    POSITIVE LOGITS
     serotonin
    0.81
    teness
    0.78
    cephal
    0.76
     wrench
    0.74
     crate
    0.72
     dam
    0.70
     mosqu
    0.70
     coffin
    0.69
     Helen
    0.69
    ï¸
    0.69
    Act Density 0.020%

    No Known Activations