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

    Neuronpedia

    INDEX
    Explanations

    phrases related to shedding light on a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to shedding light on important social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    --+
    -0.81
    ée
    -0.80
    ivari
    -0.78
    onna
    -0.69
    hold
    -0.69
    otti
    -0.69
    jump
    -0.66
    naissance
    -0.66
    win
    -0.65
    soever
    -0.65
    POSITIVE LOGITS
     shortcomings
    1.16
     hypocrisy
    1.16
     misconceptions
    1.12
     contradictions
    1.10
     flaws
    1.09
     discrepancies
    1.06
     inconsistencies
    1.05
     injust
    1.04
     absurdity
    1.02
     misogyny
    1.00
    Act Density 0.340%

    No Known Activations