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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture, specifically related to television shows and movie production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawer
    -0.18
    ãĥIJãĥ¼
    -0.17
    ziej
    -0.17
    SSF
    -0.16
    rale
    -0.16
    zie
    -0.15
    xbf
    -0.15
    ncy
    -0.15
    .cloudflare
    -0.15
    thood
    -0.15
    POSITIVE LOGITS
     interview
    0.32
     speaking
    0.32
     Speaking
    0.31
    Speaking
    0.29
     interviewed
    0.28
     Interview
    0.28
     spoke
    0.27
     told
    0.26
     speak
    0.24
     interviews
    0.23
    Act Density 0.274%

    No Known Activations