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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing equality or similarity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TRIBUN
    -0.70
    ScopeManager
    -0.69
    RepeatedField
    -0.63
    DateField
    -0.61
    ">//
    -0.61
    InputTagHelper
    -0.60
     regressions
    -0.59
     Majefty
    -0.58
     Económica
    -0.58
     AssemblyTitle
    -0.58
    POSITIVE LOGITS
    AreEqual
    0.61
     difference
    0.58
     Same
    0.57
     одина
    0.55
     onBind
    0.55
     cùng
    0.54
    Same
    0.53
    erta
    0.52
     SAME
    0.52
    相同的
    0.52
    Act Density 0.218%

    No Known Activations