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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movements or relocations of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pact
    -0.75
    ionic
    -0.67
    ctions
    -0.67
    ios
    -0.64
    Trust
    -0.64
    lived
    -0.63
    estate
    -0.62
    icient
    -0.62
    rences
    -0.61
    context
    -0.61
    POSITIVE LOGITS
     away
    1.05
     aside
    0.89
     ashore
    0.83
     onward
    0.82
     awa
    0.81
     upright
    0.81
    onto
    0.79
    Īè
    0.75
     onto
    0.74
     Away
    0.72
    Act Density 0.087%

    No Known Activations