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

    Neuronpedia

    INDEX
    Explanations

    mentions of political campaigns or candidates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a purpose or objective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KK
    -0.73
    parts
    -0.72
    fleet
    -0.72
    ashtra
    -0.71
    mare
    -0.69
    é¾
    -0.69
    cles
    -0.69
    ynski
    -0.68
    illin
    -0.68
    Contact
    -0.67
    POSITIVE LOGITS
    bidden
    1.21
    gery
    1.19
    geries
    1.07
     example
    1.04
     instance
    1.00
    gotten
    0.99
    ked
    0.89
     purposes
    0.87
     hire
    0.86
     awhile
    0.85
    Act Density 0.500%

    No Known Activations