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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by action verbs describing possession or control

    oai_token-act-pair · gpt-3.5-turbo

    references to possession or relationships involving specific characters or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocument
    -0.91
    itect
    -0.85
    webkit
    -0.71
    bender
    -0.70
    ablishment
    -0.70
     largeDownload
    -0.69
    tar
    -0.69
    inctions
    -0.69
     Reloaded
    -0.69
    lahoma
    -0.68
    POSITIVE LOGITS
     own
    1.66
     newfound
    1.09
     surroundings
    1.06
     superiors
    1.01
     favourite
    1.01
     detractors
    0.99
     teammates
    0.97
     peers
    0.96
     contemporaries
    0.96
     entire
    0.95
    Act Density 0.452%

    No Known Activations