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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions and movement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iciency
    -0.70
    nia
    -0.66
    omial
    -0.66
    oured
    -0.61
    Condition
    -0.58
    conn
    -0.57
    oys
    -0.57
    lder
    -0.57
    vous
    -0.56
    ificial
    -0.56
    POSITIVE LOGITS
     toward
    1.40
     towards
    1.36
     away
    1.15
     forward
    1.11
     into
    1.04
     onto
    1.00
     onward
    0.97
     Towards
    0.93
     farther
    0.93
    forward
    0.92
    Act Density 4.132%

    No Known Activations