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

    Neuronpedia

    INDEX
    Explanations

    words related to technological processes and systems

    oai_token-act-pair · gpt-3.5-turbo

    statements or references related to outcomes, efficiency, and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enthusi
    -0.87
     millenn
    -0.84
    eteen
    -0.76
     dared
    -0.76
     restraint
    -0.69
    intend
    -0.69
    lings
    -0.67
    ourge
    -0.67
    enged
    -0.67
    abouts
    -0.66
    POSITIVE LOGITS
     Therefore
    1.56
     Thus
    1.48
     Conversely
    1.45
     Consequently
    1.44
     Typically
    1.43
     Examples
    1.39
     Usually
    1.39
     Generally
    1.38
     Hence
    1.35
     Essentially
    1.34
    Act Density 0.411%

    No Known Activations