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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism and rebuke

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gins
    -0.74
    nex
    -0.71
    agate
    -0.69
    pleted
    -0.69
    iza
    -0.67
     expires
    -0.67
    enza
    -0.65
    lude
    -0.65
    strings
    -0.63
     ain
    -0.63
    POSITIVE LOGITS
     environmentalists
    1.20
     critics
    1.18
     commentators
    1.04
     conservatives
    1.03
     pundits
    1.03
     libertarians
    1.01
     economists
    1.00
     detractors
    0.98
     feminists
    0.96
     commenters
    0.96
    Act Density 0.181%

    No Known Activations