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

    Neuronpedia

    INDEX
    Explanations

    actions involving movement or physical interactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ansk
    -0.73
     Governments
    -0.65
     Residents
    -0.63
     UTC
    -0.63
    Week
    -0.62
     affiliates
    -0.60
    ERO
    -0.59
    GV
    -0.58
    erers
    -0.57
     budgets
    -0.57
    POSITIVE LOGITS
     beside
    0.99
     clutching
    0.98
     awkwardly
    0.98
     onto
    0.97
     nervously
    0.92
     cautiously
    0.86
     hes
    0.83
     crou
    0.83
     startled
    0.82
     impatient
    0.82
    Act Density 0.191%

    No Known Activations