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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing a significant change or transition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shift."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.82
     Seym
    -0.76
    gom
    -0.73
    ORED
    -0.72
    DOC
    -0.72
    gil
    -0.69
    Interstitial
    -0.68
    çĦ
    -0.67
    gdala
    -0.67
    MJ
    -0.65
    POSITIVE LOGITS
     shift
    1.01
     shifts
    0.94
     shifting
    0.93
    shift
    0.89
     gears
    0.87
    iple
    0.85
     shifted
    0.81
     shif
    0.78
     sands
    0.78
    overs
    0.77
    Act Density 0.017%

    No Known Activations