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

    Neuronpedia

    INDEX
    Explanations

    terms expressing opposition or objection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to opposition or objection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.74
     Tycoon
    -0.69
    oufl
    -0.68
    ifter
    -0.64
    seed
    -0.64
    omic
    -0.62
    mingham
    -0.61
     Corpse
    -0.60
    icle
    -0.59
    Delivery
    -0.59
    POSITIVE LOGITS
     thereto
    1.18
     to
    0.93
     vehemently
    0.89
     stren
    0.81
     vigorously
    0.73
     viewpoints
    0.72
    establishment
    0.69
    itism
    0.68
     against
    0.65
     stances
    0.65
    Act Density 0.063%

    No Known Activations