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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and their relationships to equations or mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.62
     Harp
    -0.57
     about
    -0.56
    caches
    -0.56
    </code>
    -0.55
     Bourgoin
    -0.55
     Wer
    -0.53
     Chwiliwch
    -0.53
    Controllo
    -0.53
    发表于
    -0.52
    POSITIVE LOGITS
     getRule
    0.78
    GenerationType
    0.78
    lotl
    0.77
    PickerController
    0.72
    trex
    0.71
    ximity
    0.71
    jandra
    0.70
    GYPT
    0.70
     Loth
    0.70
    ViewFeatures
    0.70
    Act Density 0.070%

    No Known Activations