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

    Neuronpedia

    INDEX
    Explanations

    words related to political matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political issues and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shall
    -0.73
     Lotus
    -0.70
    upon
    -0.70
    amination
    -0.69
    ERY
    -0.68
    plan
    -0.67
     Trinity
    -0.66
    wolves
    -0.66
    val
    -0.66
     Vikings
    -0.66
    POSITIVE LOGITS
     speaking
    0.84
     correct
    0.83
     driven
    0.82
     challenging
    0.79
     motivated
    0.78
     challenged
    0.78
     handic
    0.77
     engineered
    0.76
     disag
    0.76
     opposed
    0.75
    Act Density 0.010%

    No Known Activations