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

    Neuronpedia

    INDEX
    Explanations

    the word "previously" or variations of it, indicating past actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instances of the word "previously"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ocracy
    -0.74
    eer
    -0.68
    ueller
    -0.68
     Tycoon
    -0.67
    ribution
    -0.65
    roller
    -0.64
    lua
    -0.63
     Miracle
    -0.62
     Citation
    -0.62
     Solution
    -0.62
    POSITIVE LOGITS
     unsus
    0.93
     exting
    0.88
     encountered
    0.85
     held
    0.84
     incarcerated
    0.84
     disclosed
    0.84
     alluded
    0.84
    cedented
    0.83
     booked
    0.83
     unpublished
    0.82
    Act Density 0.029%

    No Known Activations