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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mathematical conditions and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agi
    -0.15
    ectl
    -0.15
    ãĥ³ãĥĦ
    -0.15
    lage
    -0.14
    UNK
    -0.14
    ertest
    -0.14
     AÄŁ
    -0.14
    onda
    -0.14
    bootstrap
    -0.14
    UNC
    -0.14
    POSITIVE LOGITS
     conditions
    0.22
    conditions
    0.18
     condition
    0.17
    æĿ¡ä»¶
    0.17
     Conditions
    0.17
     CONDITIONS
    0.17
    Conditions
    0.16
    .conditions
    0.16
     lo
    0.16
     Desc
    0.16
    Act Density 0.102%

    No Known Activations