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

    Neuronpedia

    INDEX
    Explanations

    words related to credibility and trustworthiness

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to credibility and trustworthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NAD
    -0.61
    Story
    -0.61
     Zimmerman
    -0.57
     pity
    -0.57
     Barg
    -0.57
    ĵĺ
    -0.57
    front
    -0.54
     Peninsula
    -0.53
     Vaughn
    -0.53
     ende
    -0.53
    POSITIVE LOGITS
    ibly
    1.51
    iting
    1.38
    ulously
    1.38
    uced
    1.31
    itable
    1.23
    ibles
    1.22
    ibility
    1.21
    ulous
    1.21
    entials
    1.19
    itational
    1.13
    Act Density 0.038%

    No Known Activations