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

    Neuronpedia

    INDEX
    Explanations

    phrases describing something as significant or portraying it in a particular light

    oai_token-act-pair · gpt-3.5-turbo

    articles and indefinite pronouns used to introduce or emphasize nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    items
    -0.88
    coins
    -0.86
    iffs
    -0.85
    edit
    -0.80
    mentioned
    -0.79
    ants
    -0.79
    words
    -0.79
    bots
    -0.79
    âĿ
    -0.77
    Edit
    -0.76
    POSITIVE LOGITS
     precursor
    1.05
    versive
    0.97
     continuation
    0.93
     roadmap
    0.91
     legitimate
    0.89
     mixture
    0.88
     mere
    0.88
     continuum
    0.87
     gateway
    0.87
     threat
    0.87
    Act Density 0.198%

    No Known Activations