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

    Neuronpedia

    INDEX
    Explanations

    numerical values, such as amounts or percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate various types of offerings or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STER
    -0.73
    aten
    -0.72
    ï¸ı
    -0.66
    strap
    -0.65
    eme
    -0.64
    eco
    -0.61
     Ern
    -0.60
    _-
    -0.60
    js
    -0.59
    ARGET
    -0.58
    POSITIVE LOGITS
     condolences
    0.99
     congratulations
    0.89
     parting
    0.89
     unconditional
    0.88
     nonex
    0.77
     complimentary
    0.76
     alternatives
    0.74
     warranties
    0.74
     tantal
    0.73
     unres
    0.72
    Act Density 0.170%

    No Known Activations