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

    Neuronpedia

    INDEX
    Explanations

    locations or points in texts where a shift or transition occurs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating location or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hunter
    -0.63
    mage
    -0.62
    mob
    -0.59
     trave
    -0.58
    Bug
    -0.57
    bug
    -0.57
    Abyss
    -0.56
    morph
    -0.56
    iencies
    -0.56
     disapprove
    -0.56
    POSITIVE LOGITS
    ESA
    0.75
    ulic
    0.74
    liest
    0.72
    ioned
    0.71
    anos
    0.67
    SPONSORED
    0.66
    ITAL
    0.66
    risis
    0.65
    essional
    0.64
    arters
    0.64
    Act Density 0.054%

    No Known Activations