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

    Neuronpedia

    INDEX
    Explanations

    strong verbs related to taking action or influencing decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.69
     crane
    -0.63
     KR
    -0.61
     withd
    -0.60
     Mehran
    -0.60
     foremost
    -0.59
    ItemTracker
    -0.59
     brow
    -0.58
     Diver
    -0.58
     chast
    -0.57
    POSITIVE LOGITS
    ments
    1.77
    ings
    1.76
    able
    1.67
    ables
    1.60
    ability
    1.45
    ances
    1.39
    ment
    1.34
    ational
    1.34
    ations
    1.33
    ement
    1.30
    Act Density 0.487%

    No Known Activations