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

    Neuronpedia

    INDEX
    Explanations

    phrases related to broad and impactful actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    references to extensive or comprehensive changes and reforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dar
    -0.79
    tt
    -0.75
    mate
    -0.74
     Beta
    -0.72
    Beta
    -0.69
     Embassy
    -0.69
     correspond
    -0.67
    ______
    -0.66
    mma
    -0.65
    References
    -0.64
    POSITIVE LOGITS
     sweeping
    3.82
     sweep
    1.64
     sweeps
    1.48
     swept
    1.44
     swirling
    1.43
     gripping
    1.43
     sprawling
    1.35
     expansive
    1.33
     soaring
    1.33
    swe
    1.31
    Act Density 0.021%

    No Known Activations