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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of the future in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recent
    -0.23
     lately
    -0.22
    recent
    -0.20
     latest
    -0.19
     earlier
    -0.18
     contemporary
    -0.17
     recently
    -0.17
    latest
    -0.17
    lap
    -0.16
    outers
    -0.16
    POSITIVE LOGITS
    irá
    0.17
    asty
    0.15
     directions
    0.15
     greatness
    0.15
    (after
    0.15
     possibile
    0.15
    aming
    0.14
    ewise
    0.14
    -proof
    0.14
     skyline
    0.14
    Act Density 0.094%

    No Known Activations