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

    Neuronpedia

    INDEX
    Explanations

    words related to critique and negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with morality and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [+
    -0.83
     cryst
    -0.83
    razil
    -0.74
     proble
    -0.71
    ovo
    -0.67
    âĹ¼
    -0.67
    etooth
    -0.66
     disadvant
    -0.66
    utra
    -0.65
    .....
    -0.64
    POSITIVE LOGITS
     optimism
    0.81
     partisans
    0.79
     tales
    0.78
     prag
    0.78
     spectacle
    0.77
     virtues
    0.77
     obscurity
    0.76
     indifference
    0.75
     popul
    0.75
     nostalgia
    0.74
    Act Density 0.492%

    No Known Activations