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

    Neuronpedia

    INDEX
    Explanations

    references to going back in time or returning to a previous state or location

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "the past" or nostalgic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    among
    -0.73
    ÏĢ
    -0.69
    %:
    -0.67
    Interstitial
    -0.63
     Proud
    -0.62
    Brother
    -0.62
     Brilliant
    -0.62
    âĦ¢:
    -0.61
     apart
    -0.61
     furthermore
    -0.60
    POSITIVE LOGITS
     fray
    0.96
     basics
    0.86
     haunt
    0.85
     fold
    0.84
     drawing
    0.82
     whence
    0.73
     bearings
    0.73
     original
    0.72
     senses
    0.71
     recollection
    0.70
    Act Density 0.167%

    No Known Activations