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

    Neuronpedia

    INDEX
    Explanations

    references to well-known newspapers and magazines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Bridge
    -0.15
    ãĥĬãĥ«
    -0.14
    xcf
    -0.14
     ç½
    -0.14
    .Azure
    -0.13
    adians
    -0.13
    ê´
    -0.13
    adox
    -0.13
    dorf
    -0.13
    idden
    -0.13
    POSITIVE LOGITS
     Guardian
    0.36
     Telegraph
    0.34
     Mail
    0.32
     guardian
    0.31
     Evening
    0.29
    Guard
    0.29
    Tele
    0.28
     Sunday
    0.27
    Mail
    0.27
     Observer
    0.27
    Act Density 0.099%

    No Known Activations