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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or critiques regarding films and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coli
    -0.16
    cona
    -0.15
    ÙĪÙĦا
    -0.15
    ijn
    -0.14
    ARGET
    -0.14
    dater
    -0.13
    ãĥ³ãĤº
    -0.13
    amel
    -0.13
    ën
    -0.13
    lech
    -0.13
    POSITIVE LOGITS
    inz
    0.15
    áte
    0.15
     Comparable
    0.15
    cho
    0.14
    bas
    0.14
    -fontawesome
    0.14
    atables
    0.14
     fault
    0.13
    oom
    0.13
    itty
    0.13
    Act Density 0.126%

    No Known Activations