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

    Neuronpedia

    INDEX
    Explanations

    common verbs in past tense

    oai_token-act-pair · gpt-3.5-turbo

    indications of possession or authorship, particularly the phrase "has" followed by varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wake
    -0.75
    seless
    -0.69
    acceptable
    -0.67
    wrap
    -0.65
    OOL
    -0.64
     guiName
    -0.64
     Recap
    -0.63
    cus
    -0.62
    uating
    -0.62
    ooks
    -0.61
    POSITIVE LOGITS
     been
    1.40
     undergone
    1.17
     lived
    1.14
     battled
    1.13
     resided
    1.12
     participated
    1.12
     worked
    1.12
     amassed
    1.10
     toured
    1.10
     campaigned
    1.09
    Act Density 0.214%

    No Known Activations