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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term commitments or future expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regular
    -0.15
    vé
    -0.15
    ssi
    -0.15
    omi
    -0.15
    arest
    -0.15
     regularly
    -0.14
    лив
    -0.14
    uby
    -0.14
     regular
    -0.13
     earlier
    -0.13
    POSITIVE LOGITS
     future
    0.29
    future
    0.26
    .future
    0.23
     generations
    0.22
     forever
    0.21
     tomorrow
    0.21
     lifelong
    0.20
    æľªæĿ¥
    0.20
     years
    0.20
     until
    0.19
    Act Density 0.110%

    No Known Activations