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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships emphasized with the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anden
    -0.17
    rst
    -0.15
    alt
    -0.14
    asts
    -0.14
    st
    -0.14
     både
    -0.14
    olated
    -0.13
    å¹¹
    -0.13
    ssc
    -0.13
    ems
    -0.13
    POSITIVE LOGITS
    /or
    0.73
    /OR
    0.39
    rew
    0.31
    rog
    0.30
    /of
    0.30
    наÑĩе
    0.30
    rogen
    0.29
    hra
    0.27
    erson
    0.27
    /o
    0.25
    Act Density 1.944%

    No Known Activations