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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical or computational topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various types of measurements and metrics in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overtime
    -0.70
     agre
    -0.68
     toile
    -0.67
     neighb
    -0.66
     wet
    -0.66
     wip
    -0.66
     retard
    -0.65
     destro
    -0.63
     obscene
    -0.62
     star
    -0.61
    POSITIVE LOGITS
    ccording
    1.14
    ////////////////////////////////
    0.98
    Advertisements
    0.97
    Whether
    0.97
    Spoiler
    0.97
    Asset
    0.97
    Since
    0.95
    ========
    0.95
    Given
    0.94
    There
    0.94
    Act Density 0.232%

    No Known Activations