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

    Neuronpedia

    INDEX
    Explanations

    proper names related to companies or brands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or brands, particularly those associated with news and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.89
    imir
    -0.85
    hens
    -0.84
    ork
    -0.74
    intosh
    -0.73
    iro
    -0.71
    ingly
    -0.71
    ĪĴ
    -0.70
    agna
    -0.69
    ery
    -0.68
    POSITIVE LOGITS
    glass
    0.74
    vier
    0.72
    ufact
    0.71
     Tou
    0.68
    ainer
    0.68
     Reuters
    0.66
    sonian
    0.65
    CLASS
    0.64
    baum
    0.64
    Charges
    0.64
    Act Density 0.113%

    No Known Activations