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

    Neuronpedia

    INDEX
    Explanations

    words indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omain
    -0.17
    rift
    -0.16
    licative
    -0.15
    adele
    -0.15
    room
    -0.15
    ÑĢей
    -0.15
    zim
    -0.14
    restricted
    -0.14
    rooms
    -0.14
    евиÑĩ
    -0.14
    POSITIVE LOGITS
    izia
    0.16
    æĬľ
    0.15
    velle
    0.14
    dou
    0.14
    enan
    0.14
     dou
    0.14
    ãĥģãĥ¥
    0.14
    uilt
    0.14
    길
    0.14
    Ø·ØŃ
    0.14
    Act Density 0.000%

    No Known Activations