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

    Neuronpedia

    INDEX
    Explanations

    specific symbols, punctuation, and special formatting used in mathematical or technical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.60
    RuleContext
    -0.52
    RegressionTest
    -0.50
     juſ
    -0.49
     tranſ
    -0.47
     ſever
    -0.47
    ükemmel
    -0.43
     CreateTagHelper
    -0.43
     houſe
    -0.42
     inſ
    -0.41
    POSITIVE LOGITS
    ########.
    0.54
    ۜ
    0.52
     Stoll
    0.48
    Gruss
    0.48
    carpa
    0.46
    astify
    0.46
    AccessFile
    0.46
    
    0.46
    mapStateToProps
    0.45
     Monteiro
    0.45
    Act Density 1.502%

    No Known Activations