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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or change over time

    oai_token-act-pair · gpt-3.5-turbo

    expressions of current knowledge and awareness about events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.69
    imo
    -0.67
    PLIED
    -0.65
    ricular
    -0.64
     operation
    -0.62
     Crush
    -0.62
     Jordanian
    -0.59
    stroke
    -0.59
    obbies
    -0.58
     sabotage
    -0.58
    POSITIVE LOGITS
     ourselves
    1.08
     electing
    0.77
     glimpse
    0.77
     glimps
    0.77
     presume
    0.77
    blogs
    0.74
     democracies
    0.71
     witnessing
    0.71
    ptions
    0.70
     incarcer
    0.68
    Act Density 0.421%

    No Known Activations