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

    Neuronpedia

    INDEX
    Explanations

    words related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    words related to deviation or divergence from a standard or norm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Taxi
    -0.69
    Pak
    -0.66
     Hoffman
    -0.63
     alert
    -0.62
     Briggs
    -0.61
     Ze
    -0.60
     Islamabad
    -0.59
     Fair
    -0.58
     Auto
    -0.58
     Zimmer
    -0.57
    POSITIVE LOGITS
    soever
    1.10
    iple
    0.85
    license
    0.84
    iscopal
    0.83
    ortion
    0.82
    ciating
    0.80
    ulations
    0.79
    minist
    0.79
    sylvania
    0.79
    amental
    0.78
    Act Density 0.061%

    No Known Activations