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

    Neuronpedia

    INDEX
    Explanations

    mentions of additional or extra information or resources

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "additional" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cture
    -0.70
    athon
    -0.68
     Alone
    -0.68
     Gone
    -0.68
    generic
    -0.67
    bane
    -0.67
    =-=-=-=-=-=-=-=-
    -0.67
    lua
    -0.66
    abad
    -0.66
    bows
    -0.65
    POSITIVE LOGITS
    judicial
    1.02
     impetus
    0.92
     installments
    0.86
    ordinary
    0.84
     layers
    0.82
     complication
    0.80
     information
    0.78
     expense
    0.78
     avenues
    0.76
     exposure
    0.75
    Act Density 0.023%

    No Known Activations