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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contractual obligations and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Counterfactual statements using "if" or similar words

    np_acts-logits-general · gemini-2.0-flash

    past conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.99
    MessageTagHelper
    -0.95
    parsedMessage
    -0.84
    StructEnd
    -0.83
     nahilalakip
    -0.83
    PerformLayout
    -0.83
    EndGlobalSection
    -0.82
    setVerticalGroup
    -0.81
     kasarigan
    -0.80
    webElementXpaths
    -0.77
    POSITIVE LOGITS
     hätte
    1.32
     hubiera
    1.16
     hubieran
    1.12
     hätten
    1.08
     had
    1.06
     volna
    1.03
     hubiese
    1.01
     aurait
    1.00
     gdyby
    1.00
     hadn
    1.00
    Act Density 0.350%

    No Known Activations