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

    Neuronpedia

    INDEX
    Explanations

    negative reactions or controversies

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public outrage and controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.66
     Discipline
    -0.62
     compliment
    -0.57
     carrot
    -0.57
     totality
    -0.57
     sole
    -0.57
     complement
    -0.57
    ©¶æ
    -0.57
    cknow
    -0.56
     iterator
    -0.55
    POSITIVE LOGITS
     among
    1.23
     amongst
    1.16
    among
    1.09
     across
    0.96
     internationally
    0.86
     nationally
    0.85
     elsewhere
    0.84
     abroad
    0.84
     nationwide
    0.84
     worldwide
    0.81
    Act Density 0.192%

    No Known Activations