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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to taking action

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Viz
    -0.58
     Travels
    -0.58
    mma
    -0.57
    Rush
    -0.56
    ĺħ
    -0.55
     unbeliev
    -0.55
    Raven
    -0.55
    ORK
    -0.54
    FTWARE
    -0.54
     HAR
    -0.54
    POSITIVE LOGITS
     nevertheless
    1.31
     nonetheless
    1.26
     cautioned
    1.16
     also
    0.99
     retains
    0.97
     still
    0.96
     lacks
    0.95
     concedes
    0.94
     lacked
    0.93
     fails
    0.92
    Act Density 0.194%

    No Known Activations