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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a significant change or transition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shift" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.75
    ORED
    -0.74
    gom
    -0.73
    CRIP
    -0.71
    amina
    -0.71
    gdala
    -0.69
     Seym
    -0.66
    gil
    -0.64
     jug
    -0.63
    çĦ
    -0.62
    POSITIVE LOGITS
     gears
    1.11
     shift
    0.96
     sands
    0.94
     shifts
    0.83
     away
    0.83
    otom
    0.81
     shifting
    0.81
    olitics
    0.78
     blame
    0.78
     toward
    0.77
    Act Density 0.044%

    No Known Activations