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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances and references to the term "born"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.64
     degraded
    -0.64
    oter
    -0.64
    strip
    -0.63
    ioxide
    -0.60
    aito
    -0.60
    arty
    -0.60
     Adv
    -0.59
     battered
    -0.59
    olicy
    -0.58
    POSITIVE LOGITS
    born
    1.39
    lings
    1.02
    ness
    1.00
    nesses
    0.99
    stellar
    0.94
    Born
    0.90
    stein
    0.86
    furt
    0.82
    lisher
    0.81
    tons
    0.80
    Act Density 0.008%

    No Known Activations