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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "representative"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority or government representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osure
    -0.89
    fters
    -0.74
    strap
    -0.72
    terson
    -0.70
    fall
    -0.69
    tered
    -0.68
    oner
    -0.68
    neys
    -0.68
     Pound
    -0.68
    INESS
    -0.67
    POSITIVE LOGITS
    hips
    1.06
     Kislyak
    0.81
    atives
    0.78
    onse
    0.76
     representing
    0.75
    atures
    0.75
    clinton
    0.75
    ative
    0.73
    Represent
    0.72
     thereof
    0.72
    Act Density 0.041%

    No Known Activations