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

    Neuronpedia

    INDEX
    Explanations

    terms related to conservative or consensus viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cons" and its variations, indicating a focus on consumer-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WOOD
    -0.78
     horses
    -0.69
     Meadow
    -0.67
     Hoover
    -0.65
    ILLE
    -0.63
     Pegasus
    -0.62
     feed
    -0.62
    dogs
    -0.62
     Carnegie
    -0.61
     Lup
    -0.61
    POSITIVE LOGITS
    ervatives
    1.37
    piracy
    1.35
    ensual
    1.34
    umers
    1.28
    cientious
    1.28
    ensus
    1.24
    idered
    1.21
    istent
    1.18
    ervative
    1.17
    umption
    1.10
    Act Density 0.009%

    No Known Activations