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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate an action or decision taken by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Quote
    -0.72
    burse
    -0.71
     Digest
    -0.66
     Saying
    -0.66
     Comment
    -0.65
    soever
    -0.65
    entary
    -0.64
    comment
    -0.64
     Inqu
    -0.61
    current
    -0.61
    POSITIVE LOGITS
     stumbled
    1.26
     solved
    1.25
     succeeded
    1.24
     regained
    1.23
     reached
    1.19
     achieved
    1.18
     mastered
    1.18
     gotten
    1.14
     dodged
    1.14
     underestimated
    1.14
    Act Density 0.209%

    No Known Activations