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

    Neuronpedia

    INDEX
    Explanations

    phrases related to systems, policies, or strategies in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ainen
    -0.15
    ymoon
    -0.15
    kre
    -0.14
    //{{
    -0.14
    Ñĩим
    -0.14
    Scaled
    -0.13
    é¨
    -0.13
    Îļα
    -0.13
    ANNOT
    -0.13
     kre
    -0.13
    POSITIVE LOGITS
     indeed
    0.18
     GRAT
    0.15
    vez
    0.15
    ÆĴ
    0.15
    loe
    0.14
    inde
    0.14
    oor
    0.14
     ãĥ¾
    0.14
    üss
    0.14
    ORIZED
    0.14
    Act Density 0.350%

    No Known Activations