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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating actions or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     happening
    -0.62
     REALLY
    -0.53
     there
    -0.52
     doing
    -0.52
     something
    -0.49
     molé
    -0.49
     dzie
    -0.48
     söyl
    -0.48
     There
    -0.47
    ViewModels
    -0.47
    POSITIVE LOGITS
    InjectAttribute
    1.00
    fjspx
    0.96
     Roskov
    0.93
    LookAnd
    0.89
    ganu
    0.83
    EndGlobalSection
    0.83
     AssemblyCompany
    0.79
    principalColumn
    0.79
    setVerticalGroup
    0.78
    ंदीखरीदारी
    0.77
    Act Density 1.311%

    No Known Activations