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

    Neuronpedia

    INDEX
    Explanations

    terms related to various professional fields and industries

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to crime, substance use, and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Engineers
    -0.59
    ãģĻ
    -0.59
     ..."
    -0.56
    lihood
    -0.56
    î
    -0.55
    Native
    -0.54
    La
    -0.54
    Enlarge
    -0.53
    ]."
    -0.53
    ---
    -0.53
    POSITIVE LOGITS
     rul
    0.72
    ensibly
    0.64
     glim
    0.62
     condem
    0.62
    ague
    0.59
     fared
    0.59
    ahime
    0.57
    ritical
    0.57
     survives
    0.57
    holder
    0.56
    Act Density 2.544%

    No Known Activations