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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critique or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    elements related to context and tonal shifts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imeter
    -0.79
    imeters
    -0.74
    illary
    -0.74
    essional
    -0.73
    Detailed
    -0.72
    SPONSORED
    -0.67
    Newsletter
    -0.66
    ancial
    -0.65
    Advertisements
    -0.62
    è¦ļéĨĴ
    -0.62
    POSITIVE LOGITS
     Herrera
    0.71
     ours
    0.70
     TODAY
    0.66
     Rober
    0.65
    today
    0.65
     tonight
    0.64
    ilipp
    0.63
     here
    0.62
     nowadays
    0.61
     Maduro
    0.61
    Act Density 0.675%

    No Known Activations