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

    Neuronpedia

    INDEX
    Explanations

    mentions of political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    statements related to the presence and actions of terrorist groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.60
     afore
    -0.59
    !'
    -0.56
    )--
    -0.56
    ').
    -0.55
    ominated
    -0.54
    ?),
    -0.54
    .'"
    -0.52
    ?'
    -0.52
    .'
    -0.51
    POSITIVE LOGITS
     "
    0.65
     "[
    0.64
     "âĢ¦
    0.59
    ¬¼
    0.58
     "#
    0.57
     "...
    0.57
    wcs
    0.57
     misunderstood
    0.56
     urgently
    0.56
    NetMessage
    0.54
    Act Density 1.629%

    No Known Activations