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

    Neuronpedia

    INDEX
    Explanations

    references to television and media consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tumblr
    -0.15
    cket
    -0.14
    atsby
    -0.13
    ervlet
    -0.13
    ilder
    -0.13
    aukee
    -0.13
    ToFile
    -0.13
    ippi
    -0.12
    AFE
    -0.12
    itm
    -0.12
    POSITIVE LOGITS
     TV
    0.82
     television
    0.82
     tv
    0.75
    TV
    0.70
     Television
    0.68
     Tv
    0.67
    tv
    0.62
    -TV
    0.61
     televis
    0.59
    ãĥĨãĥ¬ãĥĵ
    0.59
    Act Density 0.385%

    No Known Activations