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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change or evolution over time

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to change and evolution over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.70
    wered
    -0.69
    hemy
    -0.65
    cott
    -0.65
    çīĪ
    -0.61
    odore
    -0.60
    ostics
    -0.60
    oken
    -0.59
    boa
    -0.59
    ij士
    -0.59
    POSITIVE LOGITS
     depending
    1.39
     unpredict
    1.31
     dynamically
    1.23
    depending
    1.11
     independently
    1.01
     fluct
    0.99
     accordingly
    0.99
     differently
    0.98
     based
    0.97
     throughout
    0.96
    Act Density 0.343%

    No Known Activations