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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with controversy or debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.15
    ,
    -0.15
    oba
    -0.13
    259
    -0.13
    -loaded
    -0.13
    à¥ĭà¤Ĥ,
    -0.13
    -ÑĤо
    -0.12
     indeed
    -0.12
    .Logf
    -0.12
    責
    -0.12
    POSITIVE LOGITS
    lsru
    0.18
    cken
    0.15
    ftware
    0.15
    ordes
    0.14
    leta
    0.14
    bsites
    0.14
    óng
    0.14
    akening
    0.14
    uiltin
    0.13
     PROCUREMENT
    0.13
    Act Density 0.164%

    No Known Activations