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

    Neuronpedia

    INDEX
    Explanations

    mentions of mixing or combinations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     akade
    -0.56
     biograf
    -0.51
     biografi
    -0.50
     solidar
    -0.50
     akut
    -0.48
     geograf
    -0.48
     gole
    -0.48
     kriminal
    -0.47
     vermel
    -0.47
     kosme
    -0.47
    POSITIVE LOGITS
     mix
    1.20
     Mix
    1.18
     MIX
    1.15
     mixes
    1.14
    Mix
    1.12
    mix
    1.11
     mixing
    1.07
     mixed
    1.03
    MIX
    1.03
    mixed
    0.98
    Act Density 0.078%

    No Known Activations