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

    Neuronpedia

    INDEX
    Explanations

    proper names or nouns related to personal and professional identities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "unseal" and references to a specific individual named Jorge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glas
    -0.90
    heid
    -0.85
    ãĤ¿
    -0.84
    chel
    -0.83
    isode
    -0.82
    ãĥ¼ãĥ³
    -0.82
    cone
    -0.79
    hops
    -0.78
    itone
    -0.77
    azines
    -0.76
    POSITIVE LOGITS
    ILLE
    0.81
    ributed
    0.68
     contagious
    0.68
     Tide
    0.65
     vir
    0.65
    arily
    0.64
    Cath
    0.64
     polarized
    0.64
    tor
    0.64
    vy
    0.62
    Act Density 0.043%

    No Known Activations