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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions taken by individuals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    testcase
    -0.52
     roba
    -0.52
     Verhält
    -0.49
    atchi
    -0.49
     carico
    -0.47
     fills
    -0.45
     حد
    -0.45
     rêves
    -0.44
     Me
    -0.43
    が目
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.86
     محفوظة
    0.79
    DllImport
    0.72
    Kjelder
    0.68
    Życiorys
    0.66
    WebVitals
    0.65
    èdia
    0.65
    TestingModule
    0.65
    IntoConstraints
    0.65
    ContentAsync
    0.64
    Act Density 0.041%

    No Known Activations