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

    Neuronpedia

    INDEX
    Explanations

    mentions of political statements or positions within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of political terminology and references to political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.75
    ":[
    -0.65
    Sep
    -0.58
     (?,
    -0.57
    ascus
    -0.56
    romeda
    -0.56
    enes
    -0.55
    Interest
    -0.54
    pard
    -0.53
    Picture
    -0.52
    POSITIVE LOGITS
    !).
    1.08
    ?).
    1.01
    !),
    0.89
    !)
    0.86
    ?)
    0.85
    ).
    0.83
     ).
    0.81
    )</
    0.80
    -)
    0.77
    ?),
    0.76
    Act Density 0.975%

    No Known Activations