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

    Neuronpedia

    INDEX
    Explanations

    sentences related to political statements and decisions

    oai_token-act-pair · gpt-3.5-turbo

    legislative and policy-related discussions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !'
    -0.85
    !'"
    -0.71
    ?'
    -0.66
    .'
    -0.64
    )'
    -0.60
    ?'"
    -0.58
    .'"
    -0.58
    ,'
    -0.57
    ').
    -0.55
    .—
    -0.55
    POSITIVE LOGITS
     "[
    0.88
     "âĢ¦
    0.86
     "
    0.84
     "...
    0.82
     anecd
    0.81
     "'
    0.81
     "#
    0.72
     "(
    0.72
    ItemTracker
    0.66
     ''
    0.65
    Act Density 1.601%

    No Known Activations