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

    Neuronpedia

    INDEX
    Explanations

    references to perceiving or witnessing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Poehler
    -0.73
    ὴν
    -0.73
    endregion
    -0.72
    ništvo
    -0.71
     télécharge
    -0.71
     universitarios
    -0.70
     Krieger
    -0.70
     dimentic
    -0.68
    viaje
    -0.67
    limate
    -0.67
    POSITIVE LOGITS
     saw
    2.10
     seen
    2.10
     sees
    1.98
    Saw
    1.91
     Seen
    1.83
    saw
    1.82
    Seen
    1.80
     seeing
    1.80
     SEEN
    1.80
     Sees
    1.79
    Act Density 0.134%

    No Known Activations