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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to kindness initiatives or programs

    oai_token-act-pair · gpt-3.5-turbo

    references to kindness and related themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfavorable
    -0.76
     aligned
    -0.75
     approving
    -0.73
     acknow
    -0.71
     mentally
    -0.70
     intensive
    -0.70
     obligated
    -0.68
     proportional
    -0.67
     cour
    -0.67
     related
    -0.67
    POSITIVE LOGITS
     Productions
    1.05
     Syndrome
    1.04
     Orchestra
    1.00
    eworks
    1.00
    oeuv
    0.97
    uctions
    0.97
     Collection
    0.97
    ride
    0.96
    istries
    0.92
    inery
    0.92
    Act Density 0.452%

    No Known Activations