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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social responsibility and accountability

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express key conclusions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ruin
    -0.86
     desper
    -0.85
     pretended
    -0.82
    yip
    -0.81
     horrend
    -0.80
     pse
    -0.80
     undermin
    -0.79
     slightest
    -0.78
     ugly
    -0.78
     sucker
    -0.77
    POSITIVE LOGITS
     Additionally
    1.48
     Through
    1.44
     Together
    1.32
     Currently
    1.26
     Accordingly
    1.25
    Through
    1.25
     Specifically
    1.19
     Throughout
    1.19
     Beginning
    1.18
     Learn
    1.18
    Act Density 0.362%

    No Known Activations