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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instit
    -0.63
     showers
    -0.62
     reperto
    -0.61
     refunds
    -0.60
     concentrated
    -0.58
     bidding
    -0.58
     evid
    -0.58
     heads
    -0.57
     congrat
    -0.56
     headed
    -0.56
    POSITIVE LOGITS
    ggles
    1.42
    wered
    1.28
    ilet
    1.09
    pless
    1.07
    othy
    1.03
    gg
    1.00
    asted
    0.99
    lling
    0.98
    adies
    0.98
    ppers
    0.97
    Act Density 0.383%

    No Known Activations