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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that describe a change or evolution towards a particular state or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing the concept of change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parcels
    -0.86
     Guns
    -0.67
    oops
    -0.65
    #$
    -0.62
    2019
    -0.61
    hart
    -0.61
     Firearms
    -0.61
    books
    -0.60
    behind
    -0.60
     Vive
    -0.60
    POSITIVE LOGITS
     steadily
    0.92
     since
    0.80
    ĸļ
    0.79
     lately
    0.77
     markedly
    0.75
    gone
    0.75
     accustomed
    0.75
     blurred
    0.74
     considerably
    0.73
    antine
    0.70
    Act Density 0.150%

    No Known Activations