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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values and actions in the context of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doub
    -0.16
    pliers
    -0.16
     Carp
    -0.15
    tere
    -0.15
    lez
    -0.15
    uin
    -0.15
     doubly
    -0.14
    cret
    -0.14
    ieren
    -0.14
    Æ¡
    -0.14
    POSITIVE LOGITS
    ÏĢιÏĥ
    0.14
    輪
    0.14
     flood
    0.14
    vé
    0.14
    ãģĦãĤĦ
    0.14
    沿
    0.14
     latter
    0.13
    yntax
    0.13
     åŃ
    0.13
    ettel
    0.13
    Act Density 0.000%

    No Known Activations