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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explanation or clarification

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Hickey
    -0.76
    arkas
    -0.75
    RegistryLite
    -0.69
    ]")]
    -0.69
    firestore
    -0.68
     fó
    -0.67
    tagHelper
    -0.66
     MyBatis
    -0.65
    writerow
    -0.64
     Dorsey
    -0.63
    POSITIVE LOGITS
    lanations
    1.55
     explain
    1.53
    explain
    1.53
     Explain
    1.51
     explanation
    1.46
     explained
    1.45
     Explanation
    1.41
    Explain
    1.41
     Explained
    1.41
     explains
    1.38
    Act Density 0.048%

    No Known Activations