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

    Neuronpedia

    INDEX
    Explanations

    words related to political positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political figures and government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icity
    -0.65
    INGTON
    -0.62
    ASED
    -0.61
    osphere
    -0.60
    ufact
    -0.60
    izont
    -0.59
     Prev
    -0.58
    Operation
    -0.58
    aband
    -0.57
    OSS
    -0.56
    POSITIVE LOGITS
    hip
    1.47
    hips
    1.41
    mith
    1.15
    ervatives
    1.06
    paces
    0.94
    ilver
    0.94
    '
    0.90
     councils
    0.89
    ettings
    0.89
     secretaries
    0.85
    Act Density 0.204%

    No Known Activations