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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reporting and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Subsequent
    -0.83
    Later
    -0.82
     Thereafter
    -0.81
     Later
    -0.80
    recent
    -0.76
     RECENT
    -0.75
    翌
    -0.75
     Shortly
    -0.74
     Subsequently
    -0.74
    Recent
    -0.73
    POSITIVE LOGITS
     Réponses
    0.68
     this
    0.51
    ADVERTISEMENT
    0.48
     ActivatedRoute
    0.47
     in
    0.46
     lat
    0.45
     just
    0.44
     the
    0.44
    enment
    0.44
     yes
    0.44
    Act Density 0.365%

    No Known Activations