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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and geometric points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isd
    -0.15
    ittel
    -0.15
    ulla
    -0.14
    chter
    -0.14
    antee
    -0.14
    eyn
    -0.14
    ego
    -0.14
    lider
    -0.13
    гаÑĢ
    -0.13
    gren
    -0.13
    POSITIVE LOGITS
    ãģ¡ãĤī
    0.15
    iyah
    0.15
     cuck
    0.14
    мо
    0.14
    ught
    0.14
     GOODS
    0.13
     (~(
    0.13
    ัà¸ģร
    0.13
    ENTA
    0.13
    наÑħ
    0.13
    Act Density 0.013%

    No Known Activations