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

    Neuronpedia

    INDEX
    Explanations

    methodological terms and research-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PasswordEncoder
    -0.54
     שוליים
    -0.51
    setViewportView
    -0.47
    UseVisualStyle
    -0.47
     AssemblyCulture
    -0.46
     TextAlign
    -0.44
    WriteBarrier
    -0.43
    MockBean
    -0.42
    WebControls
    -0.42
    MemoryWarning
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.71
     صوتيه
    0.61
     الحره
    0.43
    Chham
    0.42
     Große
    0.39
     Besch
    0.39
     förs
    0.38
     giao
    0.37
    ernoo
    0.37
    Materiale
    0.37
    Act Density 0.976%

    No Known Activations