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

    Neuronpedia

    INDEX
    Explanations

    verbs and noun phrases related to diplomacy and assignments

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivan
    -0.65
     staggered
    -0.64
     recol
    -0.59
     rented
    -0.59
     lasted
    -0.59
     haul
    -0.59
     holiday
    -0.59
     monument
    -0.58
     renovated
    -0.58
    ija
    -0.58
    POSITIVE LOGITS
     Secondly
    0.77
     Specifically
    0.74
     Sending
    0.72
     Errors
    0.71
    science
    0.71
     Tags
    0.68
    units
    0.68
     Especially
    0.67
    parts
    0.67
     Lastly
    0.66
    Act Density 1.131%

    No Known Activations