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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "to" indicating intention or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.17
    elik
    -0.17
    raft
    -0.15
    jde
    -0.15
    .Observable
    -0.15
    riet
    -0.14
    achers
    -0.14
    kp
    -0.14
    oco
    -0.14
    omnia
    -0.14
    POSITIVE LOGITS
     conclusion
    0.24
     conclusions
    0.23
     terms
    0.17
    _rat
    0.16
     Conclusion
    0.16
     attention
    0.15
     abrupt
    0.15
     consensus
    0.15
     Howe
    0.14
     grips
    0.14
    Act Density 0.033%

    No Known Activations