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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a relationship or association with other entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weise
    -0.16
    radu
    -0.16
    616
    -0.15
    ave
    -0.15
    oman
    -0.14
    urs
    -0.14
    .showMessage
    -0.14
    å¼ı
    -0.14
    ously
    -0.14
    iland
    -0.14
    POSITIVE LOGITS
    icontrol
    0.18
    ãĤ
    0.17
    .impl
    0.16
    longleftrightarrow
    0.14
    lem
    0.14
    ozy
    0.14
    letics
    0.14
    å¢ŀ
    0.14
    iaux
    0.13
    elps
    0.13
    Act Density 0.126%

    No Known Activations