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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply relational connections and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alonso
    -0.17
    ©
    -0.17
     بستÙĩ
    -0.15
    ียร
    -0.15
    inha
    -0.14
    lap
    -0.14
    etrain
    -0.14
    thouse
    -0.14
    ãĥ¬ãĤ¹
    -0.14
     bundle
    -0.14
    POSITIVE LOGITS
    VML
    0.14
     Gund
    0.14
    abin
    0.14
    enis
    0.14
    anium
    0.14
    chemy
    0.13
    Important
    0.13
    uct
    0.13
     Trom
    0.13
    opot
    0.13
    Act Density 0.005%

    No Known Activations