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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change and upheaval

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arate
    -0.75
    arten
    -0.74
    aque
    -0.72
    antes
    -0.72
    elaide
    -0.71
    isson
    -0.71
    NB
    -0.70
     Zup
    -0.70
    itars
    -0.70
    iologist
    -0.68
    POSITIVE LOGITS
     slightest
    1.08
     ensuing
    1.00
     nascent
    0.99
     nation
    0.98
     proverbial
    0.97
     broader
    0.96
     world
    0.94
     aforementioned
    0.93
     burgeoning
    0.93
     wider
    0.92
    Act Density 0.813%

    No Known Activations