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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships between actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anta
    -0.21
    ona
    -0.17
    ante
    -0.16
    uid
    -0.16
    ingham
    -0.15
    uj
    -0.15
     me
    -0.15
    ard
    -0.14
     par
    -0.14
     la
    -0.13
    POSITIVE LOGITS
    è¿Ļä¸Ģ
    0.22
    è¿Ļ个
    0.22
     these
    0.20
     this
    0.20
     such
    0.19
     nÃły
    0.19
    è¿Ļç§į
    0.19
     ÑįÑĤого
    0.19
     ấy
    0.19
    è¿Ļæł·çļĦ
    0.19
    Act Density 0.303%

    No Known Activations