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

    Neuronpedia

    INDEX
    Explanations

    Mixing-related activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mix" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.80
     disability
    -0.75
     Leth
    -0.70
     cowardly
    -0.68
     closure
    -0.67
     handic
    -0.66
     Tro
    -0.66
    arlane
    -0.66
    ortality
    -0.65
     Retirement
    -0.65
    POSITIVE LOGITS
     Mix
    3.06
    Mix
    2.72
     mixing
    2.65
    mix
    2.53
     mixes
    2.17
     mixer
    2.04
     Remix
    1.76
     remix
    1.57
     mix
    1.41
     blending
    1.33
    Act Density 0.016%

    No Known Activations