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

    Neuronpedia

    INDEX
    Explanations

    phrases related to declines or changes in a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic fluctuations and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.70
    flix
    -0.68
    urally
    -0.67
    DN
    -0.65
    inav
    -0.63
    ove
    -0.63
    ateurs
    -0.62
    ictionary
    -0.62
    unts
    -0.62
    Family
    -0.62
    POSITIVE LOGITS
    ipolar
    0.99
     fortunes
    0.79
     slump
    0.79
     tides
    0.77
     tide
    0.76
     turbulence
    0.76
    luster
    0.76
     havoc
    0.73
     recession
    0.72
    INESS
    0.72
    Act Density 0.331%

    No Known Activations