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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on the name "Roe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DCS
    -0.81
    icago
    -0.77
     Immunity
    -0.76
     Flavoring
    -0.68
     Fortress
    -0.67
    recomm
    -0.64
    ropolitan
    -0.64
     Legion
    -0.64
    multi
    -0.64
     Improvement
    -0.63
    POSITIVE LOGITS
     Roe
    1.13
    ggy
    0.89
    ppel
    0.87
    issance
    0.83
    kus
    0.79
    pees
    0.79
    ĸļ
    0.79
    cks
    0.77
    anne
    0.75
    ptin
    0.74
    Act Density 0.009%

    No Known Activations