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

    Neuronpedia

    INDEX
    Explanations

    opinions or beliefs expressed on various topics

    oai_token-act-pair · gpt-3.5-turbo

    references to personal views or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mamm
    -0.74
    eri
    -0.72
     Dull
    -0.69
     Hamm
    -0.67
    enary
    -0.67
     Doe
    -0.66
    trap
    -0.65
     erection
    -0.63
     unbeliev
    -0.63
    amaz
    -0.62
    POSITIVE LOGITS
     beliefs
    0.99
     stances
    0.91
     viewpoints
    0.89
     expressed
    0.88
     opinions
    0.88
    odox
    0.85
     regarding
    0.83
     views
    0.83
     esp
    0.78
     concerning
    0.76
    Act Density 0.126%

    No Known Activations