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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decision making

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.77
    76561
    -0.67
    quartered
    -0.62
    teen
    -0.60
     cursing
    -0.59
     Falling
    -0.58
    estate
    -0.57
    pend
    -0.56
    backer
    -0.56
     Shooting
    -0.56
    POSITIVE LOGITS
    't
    1.25
     afford
    1.24
     safely
    1.13
     overcome
    1.05
     feas
    1.02
     improve
    1.02
     withstand
    1.00
    berra
    0.98
     replicate
    0.98
     achieve
    0.98
    Act Density 0.165%

    No Known Activations