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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing and discussing personal opinions and views

    oai_token-act-pair · gpt-3.5-turbo

    references to personal opinions or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dull
    -0.75
    trap
    -0.67
    insert
    -0.64
     unbeliev
    -0.64
    Textures
    -0.63
    cia
    -0.63
    dry
    -0.63
    eri
    -0.62
    duct
    -0.62
    Sequ
    -0.61
    POSITIVE LOGITS
     stances
    1.18
     beliefs
    1.05
     stance
    0.97
     expressed
    0.96
     opinions
    0.95
     regarding
    0.91
     views
    0.91
    odox
    0.91
     viewpoints
    0.91
     esp
    0.86
    Act Density 0.144%

    No Known Activations