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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or opposition to certain topics or actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of critics and their opinions on policies or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anniversary
    -0.72
    Ħ¢
    -0.68
     Civilization
    -0.64
    oÄŁ
    -0.60
    smith
    -0.60
     +/-
    -0.59
     increments
    -0.58
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.58
     Company
    -0.58
    ced
    -0.57
    POSITIVE LOGITS
    paces
    0.87
    ervatives
    0.84
     critics
    0.84
    hip
    0.83
    hesis
    0.82
     detractors
    0.77
     skeptics
    0.77
     supporters
    0.75
     accuse
    0.74
     assail
    0.73
    Act Density 0.042%

    No Known Activations