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

    Neuronpedia

    INDEX
    Explanations

    references to a specific news outlet named "Express"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Express"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellen
    -0.78
    aeper
    -0.77
     Ambro
    -0.71
    kees
    -0.69
    STEM
    -0.68
    abama
    -0.67
    quartered
    -0.66
     Icar
    -0.64
    tackle
    -0.63
    SOURCE
    -0.62
    POSITIVE LOGITS
    Route
    1.12
    ions
    1.09
    ivity
    0.98
    ional
    0.89
    Express
    0.88
    VPN
    0.85
    iveness
    0.84
    ivities
    0.79
    imity
    0.78
    igent
    0.77
    Act Density 0.025%

    No Known Activations