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

    Neuronpedia

    INDEX
    Explanations

    words related to political discourse and processes, particularly focusing on US politics and associated entities like Democrats and Republicans.

    oai_token-act-pair · gemini-2.0-flash

    patterns or contexts related to direction and authority

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -0.81
    UpInside
    -0.79
     pleaſure
    -0.76
     itſelf
    -0.74
     raiſ
    -0.73
     informée
    -0.73
     disambiguazione
    -0.72
     uſe
    -0.71
     ſee
    -0.71
     purpoſe
    -0.71
    POSITIVE LOGITS
     direction
    0.54
    direction
    0.49
     body
    0.48
     U
    0.47
     N
    0.47
     Am
    0.45
     House
    0.45
    EndContext
    0.44
    于
    0.44
    ump
    0.43
    Act Density 0.981%

    No Known Activations