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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to the geographical or political context of a situation

    oai_token-act-pair · gpt-3.5-turbo

    colons and phrases that suggest implications or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.75
     troubles
    -0.72
    oen
    -0.70
    ebin
    -0.70
    undai
    -0.69
    ãĤ©
    -0.66
    enium
    -0.66
     tremend
    -0.65
    apan
    -0.65
    iple
    -0.64
    POSITIVE LOGITS
     namely
    1.12
     Provided
    0.90
     Whereas
    0.79
     Stories
    0.75
     Journals
    0.72
     Countries
    0.68
     Scores
    0.68
     Writing
    0.68
     Machines
    0.68
     "âĢ¦
    0.68
    Act Density 0.104%

    No Known Activations