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

    Neuronpedia

    INDEX
    Explanations

    sentences related to criticism or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ownership and financial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miracle
    -0.87
    velt
    -0.83
    natureconservancy
    -0.81
    uclear
    -0.70
    vana
    -0.68
    ihilation
    -0.67
     miracles
    -0.67
     prest
    -0.66
     miraculous
    -0.65
     probability
    -0.65
    POSITIVE LOGITS
     dissatisfaction
    1.01
     complaints
    1.00
     lately
    0.98
     frustrations
    0.98
     dissatisfied
    0.98
    particularly
    0.96
    untled
    0.93
     mistrust
    0.93
     complained
    0.92
     reluct
    0.92
    Act Density 0.759%

    No Known Activations