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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future plans and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.45
    Panamoan
    -0.43
     lenker
    -0.43
     habrían
    -0.41
     habría
    -0.40
     приходи
    -0.40
    BufferException
    -0.38
    ьажоргаш
    -0.37
    hyrchwyd
    -0.37
    thâu
    -0.37
    POSITIVE LOGITS
    これから
    0.74
     henceforth
    0.59
    今後
    0.58
     future
    0.52
     komende
    0.50
     künftig
    0.50
     will
    0.48
    Gonna
    0.47
     zukünf
    0.47
     new
    0.45
    Act Density 0.503%

    No Known Activations