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

    Neuronpedia

    INDEX
    Explanations

    structural elements in code or data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     copy
    -0.56
     SALES
    -0.47
     Copy
    -0.46
    GTCX
    -0.46
     dealers
    -0.45
     Cooley
    -0.44
     hypers
    -0.44
     Hermans
    -0.44
    sianic
    -0.42
     precincts
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.55
    InjectAttribute
    0.54
                        
    0.47
                       
    0.46
    OGND
    0.46
     مرئيه
    0.45
    ScopeManager
    0.45
    TestingModule
    0.44
    AutoScaleMode
    0.44
                         
    0.41
    Act Density 0.534%

    No Known Activations