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

    Neuronpedia

    INDEX
    Explanations

    terms related to social welfare and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Networking
    -0.16
    .Localization
    -0.16
    çĬ¬
    -0.16
    коÑĤ
    -0.15
    quam
    -0.14
    ibal
    -0.14
    BUR
    -0.14
     Berk
    -0.14
    elas
    -0.14
    uning
    -0.14
    POSITIVE LOGITS
    रण
    0.16
    ãģĹãģ
    0.15
    ny
    0.14
     Rounds
    0.14
    orno
    0.13
    ÙħاÙħ
    0.13
     proof
    0.13
     grad
    0.13
    quier
    0.13
    atics
    0.13
    Act Density 0.030%

    No Known Activations