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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with atomic concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to atomic structure and nuclear energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fargo
    -0.78
    cific
    -0.76
    shire
    -0.74
    atche
    -0.70
    nir
    -0.68
     Angeles
    -0.68
     Cosponsors
    -0.68
    ers
    -0.66
    crow
    -0.66
    eries
    -0.64
    POSITIVE LOGITS
    ctrl
    0.87
     clocks
    0.85
    opl
    0.84
     bomb
    0.84
    ysis
    0.83
     nucle
    0.83
     latt
    0.81
     atom
    0.81
     nucleus
    0.81
     physicist
    0.79
    Act Density 0.064%

    No Known Activations