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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or development over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or conditions in history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Els
    -0.55
    onto
    -0.50
    $$$$
    -0.48
    cause
    -0.47
    senal
    -0.42
    $.
    -0.42
    ãĤ´ãĥ³
    -0.42
    emale
    -0.42
     outwe
    -0.42
    Tickets
    -0.42
    POSITIVE LOGITS
    olation
    0.46
     ][
    0.45
    Ĥİ
    0.44
    catentry
    0.43
     embodiments
    0.43
     KT
    0.42
     RELEASE
    0.42
     Pathfinder
    0.42
     Tanks
    0.41
    pires
    0.41
    Act Density 0.839%

    No Known Activations